Longbing Cao

Longbing Cao, Hui Chen, Xuhui Fan et al.

Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. However, the robustness and capabilities of existing FL methods are challenged by limited and dynamic data and conditions, complexities including heterogeneities and uncertainties, and analytical explainability. Bayesian federated learning (BFL) has emerged as a promising approach to address these issues. This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives. We categorize and discuss client- and server-side and FL-based BFL methods and their pros and cons. The limitations of the existing BFL methods and the future directions of BFL research further address the intricate requirements of real-life FL applications.

Zhangkai Wu, Longbing Cao, Lei Qi

The surrogate loss of variational autoencoders (VAEs) poses various challenges to their training, inducing the imbalance between task fitting and representation inference. To avert this, the existing strategies for VAEs focus on adjusting the tradeoff by introducing hyperparameters, deriving a tighter bound under some mild assumptions, or decomposing the loss components per certain neural settings. VAEs still suffer from uncertain tradeoff learning.We propose a novel evolutionary variational autoencoder (eVAE) building on the variational information bottleneck (VIB) theory and integrative evolutionary neural learning. eVAE integrates a variational genetic algorithm into VAE with variational evolutionary operators including variational mutation, crossover, and evolution. Its inner-outer-joint training mechanism synergistically and dynamically generates and updates the uncertain tradeoff learning in the evidence lower bound (ELBO) without additional constraints. Apart from learning a lossy compression and representation of data under the VIB assumption, eVAE presents an evolutionary paradigm to tune critical factors of VAEs and deep neural networks and addresses the premature convergence and random search problem by integrating evolutionary optimization into deep learning. Experiments show that eVAE addresses the KL-vanishing problem for text generation with low reconstruction loss, generates all disentangled factors with sharp images, and improves the image generation quality,respectively. eVAE achieves better reconstruction loss, disentanglement, and generation-inference balance than its competitors.

Hui He, Qi Zhang, Shoujin Wang et al.

Performance unfairness among variables widely exists in multivariate time series (MTS) forecasting models since such models may attend/bias to certain (advantaged) variables. Addressing this unfairness problem is important for equally attending to all variables and avoiding vulnerable model biases/risks. However, fair MTS forecasting is challenging and has been less studied in the literature. To bridge such significant gap, we formulate the fairness modeling problem as learning informative representations attending to both advantaged and disadvantaged variables. Accordingly, we propose a novel framework, named FairFor, for fairness-aware MTS forecasting. FairFor is based on adversarial learning to generate both group-independent and group-relevant representations for the downstream forecasting. The framework first leverages a spectral relaxation of the K-means objective to infer variable correlations and thus to group variables. Then, it utilizes a filtering&fusion component to filter the group-relevant information and generate group-independent representations via orthogonality regularization. The group-independent and group-relevant representations form highly informative representations, facilitating to sharing knowledge from advantaged variables to disadvantaged variables to guarantee fairness. Extensive experiments on four public datasets demonstrate the effectiveness of our proposed FairFor for fair forecasting and significant performance improvement.

Zhilin Zhao, Longbing Cao, Kun-Yu Lin

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This is mainly due to the absence of OOD samples during training, which fails to constrain the network properly. To tackle this issue, several state-of-the-art methods include adding extra OOD samples to training and assign them with manually-defined labels. However, this practice can introduce unreliable labeling, negatively affecting ID classification. The distributional vulnerability presents a critical challenge for non-IID deep learning, which aims for OOD-tolerant ID classification by balancing ID generalization and OOD detection. In this paper, we introduce a novel \textit{supervision adaptation} approach to generate adaptive supervision information for OOD samples, making them more compatible with ID samples. Firstly, we measure the dependency between ID samples and their labels using mutual information, revealing that the supervision information can be represented in terms of negative probabilities across all classes. Secondly, we investigate data correlations between ID and OOD samples by solving a series of binary regression problems, with the goal of refining the supervision information for more distinctly separable ID classes. Our extensive experiments on four advanced network architectures, two ID datasets, and eleven diversified OOD datasets demonstrate the efficacy of our supervision adaptation approach in improving both ID classification and OOD detection capabilities.

Zhilin Zhao, Longbing Cao

To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions differing from that of in-distribution samples could be assigned with unexpected high-confidence predictions because they could obtain minimum strongly label-related information. To distinguish in- and out-of-distribution samples, Dual Representation Learning (DRL) makes out-of-distribution samples harder to have high-confidence predictions by exploring both strongly and weakly label-related information from in-distribution samples. For a pretrained network exploring strongly label-related information to learn label-discriminative representations, DRL trains its auxiliary network exploring the remaining weakly label-related information to learn distribution-discriminative representations. Specifically, for a label-discriminative representation, DRL constructs its complementary distribution-discriminative representation by integrating diverse representations less similar to the label-discriminative representation. Accordingly, DRL combines label- and distribution-discriminative representations to detect out-of-distribution samples. Experiments show that DRL outperforms the state-of-the-art methods for out-of-distribution detection.

Peizhen Li, Longbing Cao, Xiao-Ming Wu et al.

Equipping humanoid robots with the capability to understand emotional states of human interactants and express emotions appropriately according to situations is essential for affective human-robot interaction. However, enabling current vision-aware multimodal emotion recognition models for affective human-robot interaction in the real-world raises embodiment challenges: addressing the environmental noise issue and meeting real-time requirements. First, in multiparty conversation scenarios, the noises inherited in the visual observation of the robot, which may come from either 1) distracting objects in the scene or 2) inactive speakers appearing in the field of view of the robot, hinder the models from extracting emotional cues from vision inputs. Secondly, realtime response, a desired feature for an interactive system, is also challenging to achieve. To tackle both challenges, we introduce an affective human-robot interaction system called UGotMe designed specifically for multiparty conversations. Two denoising strategies are proposed and incorporated into the system to solve the first issue. Specifically, to filter out distracting objects in the scene, we propose extracting face images of the speakers from the raw images and introduce a customized active face extraction strategy to rule out inactive speakers. As for the second issue, we employ efficient data transmission from the robot to the local server to improve realtime response capability. We deploy UGotMe on a human robot named Ameca to validate its real-time inference capabilities in practical scenarios. Videos demonstrating real-world deployment are available at https://lipzh5.github.io/HumanoidVLE/.

Zhilin Zhao, Longbing Cao, Kun-Yu Lin

Deep neural networks for image classification only learn to map in-distribution inputs to their corresponding ground truth labels in training without differentiating out-of-distribution samples from in-distribution ones. This results from the assumption that all samples are independent and identically distributed (IID) without distributional distinction. Therefore, a pretrained network learned from in-distribution samples treats out-of-distribution samples as in-distribution and makes high-confidence predictions on them in the test phase. To address this issue, we draw out-of-distribution samples from the vicinity distribution of training in-distribution samples for learning to reject the prediction on out-of-distribution inputs. A \textit{Cross-class Vicinity Distribution} is introduced by assuming that an out-of-distribution sample generated by mixing multiple in-distribution samples does not share the same classes of its constituents. We thus improve the discriminability of a pretrained network by finetuning it with out-of-distribution samples drawn from the cross-class vicinity distribution, where each out-of-distribution input corresponds to a complementary label. Experiments on various in-/out-of-distribution datasets show that the proposed method significantly outperforms the existing methods in improving the capacity of discriminating between in- and out-of-distribution samples.

Kun Yi, Qi Zhang, Wei Fan et al.

Time series forecasting has played the key role in different industrial, including finance, traffic, energy, and healthcare domains. While existing literatures have designed many sophisticated architectures based on RNNs, GNNs, or Transformers, another kind of approaches based on multi-layer perceptrons (MLPs) are proposed with simple structure, low complexity, and {superior performance}. However, most MLP-based forecasting methods suffer from the point-wise mappings and information bottleneck, which largely hinders the forecasting performance. To overcome this problem, we explore a novel direction of applying MLPs in the frequency domain for time series forecasting. We investigate the learned patterns of frequency-domain MLPs and discover their two inherent characteristic benefiting forecasting, (i) global view: frequency spectrum makes MLPs own a complete view for signals and learn global dependencies more easily, and (ii) energy compaction: frequency-domain MLPs concentrate on smaller key part of frequency components with compact signal energy. Then, we propose FreTS, a simple yet effective architecture built upon Frequency-domain MLPs for Time Series forecasting. FreTS mainly involves two stages, (i) Domain Conversion, that transforms time-domain signals into complex numbers of frequency domain; (ii) Frequency Learning, that performs our redesigned MLPs for the learning of real and imaginary part of frequency components. The above stages operated on both inter-series and intra-series scales further contribute to channel-wise and time-wise dependency learning. Extensive experiments on 13 real-world benchmarks (including 7 benchmarks for short-term forecasting and 6 benchmarks for long-term forecasting) demonstrate our consistent superiority over state-of-the-art methods.

Kun Yi, Qi Zhang, Wei Fan et al.

Multivariate time series (MTS) forecasting has shown great importance in numerous industries. Current state-of-the-art graph neural network (GNN)-based forecasting methods usually require both graph networks (e.g., GCN) and temporal networks (e.g., LSTM) to capture inter-series (spatial) dynamics and intra-series (temporal) dependencies, respectively. However, the uncertain compatibility of the two networks puts an extra burden on handcrafted model designs. Moreover, the separate spatial and temporal modeling naturally violates the unified spatiotemporal inter-dependencies in real world, which largely hinders the forecasting performance. To overcome these problems, we explore an interesting direction of directly applying graph networks and rethink MTS forecasting from a pure graph perspective. We first define a novel data structure, hypervariate graph, which regards each series value (regardless of variates or timestamps) as a graph node, and represents sliding windows as space-time fully-connected graphs. This perspective considers spatiotemporal dynamics unitedly and reformulates classic MTS forecasting into the predictions on hypervariate graphs. Then, we propose a novel architecture Fourier Graph Neural Network (FourierGNN) by stacking our proposed Fourier Graph Operator (FGO) to perform matrix multiplications in Fourier space. FourierGNN accommodates adequate expressiveness and achieves much lower complexity, which can effectively and efficiently accomplish the forecasting. Besides, our theoretical analysis reveals FGO's equivalence to graph convolutions in the time domain, which further verifies the validity of FourierGNN. Extensive experiments on seven datasets have demonstrated our superior performance with higher efficiency and fewer parameters compared with state-of-the-art methods.

Wei Wang, Longbing Cao

Real-life events, behaviors and interactions produce sequential data. An important but rarely explored problem is to analyze those nonoccurring (also called negative) yet important sequences, forming negative sequence analysis (NSA). A typical NSA area is to discover negative sequential patterns (NSPs) consisting of important non-occurring and occurring elements and patterns. The limited existing work on NSP mining relies on frequentist and downward closure property-based pattern selection, producing large and highly redundant NSPs, nonactionable for business decision-making. This work makes the first attempt for actionable NSP discovery. It builds an NSP graph representation, quantify both explicit occurrence and implicit non-occurrence-based element and pattern relations, and then discover significant, diverse and informative NSPs in the NSP graph to represent the entire NSP set for discovering actionable NSPs. A DPP-based NSP representation and actionable NSP discovery method EINSP introduces novel and significant contributions for NSA and sequence analysis: (1) it represents NSPs by a determinantal point process (DPP) based graph; (2) it quantifies actionable NSPs in terms of their statistical significance, diversity, and strength of explicit/implicit element/pattern relations; and (3) it models and measures both explicit and implicit element/pattern relations in the DPP-based NSP graph to represent direct and indirect couplings between NSP items, elements and patterns. We substantially analyze the effectiveness of EINSP in terms of various theoretical and empirical aspects including complexity, item/pattern coverage, pattern size and diversity, implicit pattern relation strength, and data factors.

Zhilin Zhao, Longbing Cao, Chang-Dong Wang

The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be in-distribution, while samples that deviate semantically would be identified as out-of-distribution and excluded during the annotation process. However, experts may erroneously classify these out-of-distribution samples as in-distribution, assigning them labels that are inherently unreliable. This mixture of unreliable labels and varied data types makes the task of learning robust neural networks notably challenging. We observe that both in- and out-of-distribution samples can almost invariably be ruled out from belonging to certain classes, aside from those corresponding to unreliable ground-truth labels. This opens the possibility of utilizing reliable complementary labels that indicate the classes to which a sample does not belong. Guided by this insight, we introduce a novel approach, termed \textit{Gray Learning} (GL), which leverages both ground-truth and complementary labels. Crucially, GL adaptively adjusts the loss weights for these two label types based on prediction confidence levels. By grounding our approach in statistical learning theory, we derive bounds for the generalization error, demonstrating that GL achieves tight constraints even in non-IID settings. Extensive experimental evaluations reveal that our method significantly outperforms alternative approaches grounded in robust statistics.

Rui Yu, Yifeng Li, Wenpeng Lu et al.

In natural language processing (NLP), the context of a word or sentence plays an essential role. Contextual information such as the semantic representation of a passage or historical dialogue forms an essential part of a conversation and a precise understanding of the present phrase or sentence. However, the standard attention mechanisms typically generate weights using query and key but ignore context, forming a Bi-Attention framework, despite their great success in modeling sequence alignment. This Bi-Attention mechanism does not explicitly model the interactions between the contexts, queries and keys of target sequences, missing important contextual information and resulting in poor attention performance. Accordingly, a novel and general triple-attention (Tri-Attention) framework expands the standard Bi-Attention mechanism and explicitly interacts query, key, and context by incorporating context as the third dimension in calculating relevance scores. Four variants of Tri-Attention are generated by expanding the two-dimensional vector-based additive, dot-product, scaled dot-product, and bilinear operations in Bi-Attention to the tensor operations for Tri-Attention. Extensive experiments on three NLP tasks demonstrate that Tri-Attention outperforms about 30 state-of-the-art non-attention, standard Bi-Attention, contextual Bi-Attention approaches and pretrained neural language models1.

Manqing Dong, Hao Huang, Longbing Cao

An emerging topic in large language models (LLMs) is their application to time series forecasting, characterizing mainstream and patternable characteristics of time series. A relevant but rarely explored and more challenging question is whether LLMs can detect and explain time series anomalies, a critical task across various real-world applications. In this paper, we investigate the capabilities of LLMs, specifically GPT-4 and LLaMA3, in detecting and explaining anomalies in time series. Our studies reveal that: 1) LLMs cannot be directly used for time series anomaly detection. 2) By designing prompt strategies such as in-context learning and chain-of-thought prompting, GPT-4 can detect time series anomalies with results competitive to baseline methods. 3) We propose a synthesized dataset to automatically generate time series anomalies with corresponding explanations. By applying instruction fine-tuning on this dataset, LLaMA3 demonstrates improved performance in time series anomaly detection tasks. In summary, our exploration shows the promising potential of LLMs as time series anomaly detectors.

Jiaxing Miao, Liang Hu, Qi Zhang et al.

Graph data in real-world scenarios undergo rapid and frequent changes, making it challenging for existing graph models to effectively handle the continuous influx of new data and accommodate data withdrawal requests. The approach to frequently retraining graph models is resource intensive and impractical. To address this pressing challenge, this paper introduces a new concept of graph memory learning. Its core idea is to enable a graph model to selectively remember new knowledge but forget old knowledge. Building on this approach, the paper presents a novel graph memory learning framework - Brain-inspired Graph Memory Learning (BGML), inspired by brain network dynamics and function-structure coupling strategies. BGML incorporates a multi-granular hierarchical progressive learning mechanism rooted in feature graph grain learning to mitigate potential conflict between memorization and forgetting in graph memory learning. This mechanism allows for a comprehensive and multi-level perception of local details within evolving graphs. In addition, to tackle the issue of unreliable structures in newly added incremental information, the paper introduces an information self-assessment ownership mechanism. This mechanism not only facilitates the propagation of incremental information within the model but also effectively preserves the integrity of past experiences. We design five types of graph memory learning tasks: regular, memory, unlearning, data-incremental, and class-incremental to evaluate BGML. Its excellent performance is confirmed through extensive experiments on multiple real-world node classification datasets.

Hui Chen, Hengyu Liu, Longbing Cao et al.

Bayesian personalized federated learning (BPFL) addresses challenges in existing personalized FL (PFL). BPFL aims to quantify the uncertainty and heterogeneity within and across clients towards uncertainty representations by addressing the statistical heterogeneity of client data. In PFL, some recent preliminary work proposes to decompose hidden neural representations into shared and local components and demonstrates interesting results. However, most of them do not address client uncertainty and heterogeneity in FL systems, while appropriately decoupling neural representations is challenging and often ad hoc. In this paper, we make the first attempt to introduce a general BPFL framework to decompose and jointly learn shared and personalized uncertainty representations on statistically heterogeneous client data over time. A Bayesian federated neural network BPFed instantiates BPFL by jointly learning cross-client shared uncertainty and client-specific personalized uncertainty over statistically heterogeneous and randomly participating clients. We further involve continual updating of prior distribution in BPFed to speed up the convergence and avoid catastrophic forgetting. Theoretical analysis and guarantees are provided in addition to the experimental evaluation of BPFed against the diversified baselines.

Jiwei Guan, Tianyu Ding, Longbing Cao et al.

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal attack methods have largely overlooked cross-modal interactions between visual and textual modalities, particularly in the context of cross-attention mechanisms. In this paper, we study the adversarial vulnerability of recent VLP transformers and design a novel Joint Multimodal Transformer Feature Attack (JMTFA) that concurrently introduces adversarial perturbations in both visual and textual modalities under white-box settings. JMTFA strategically targets attention relevance scores to disrupt important features within each modality, generating adversarial samples by fusing perturbations and leading to erroneous model predictions. Experimental results indicate that the proposed approach achieves high attack success rates on vision-language understanding and reasoning downstream tasks compared to existing baselines. Notably, our findings reveal that the textual modality significantly influences the complex fusion processes within VLP transformers. Moreover, we observe no apparent relationship between model size and adversarial robustness under our proposed attacks. These insights emphasize a new dimension of adversarial robustness and underscore potential risks in the reliable deployment of multimodal AI systems.

Zhilin Zhao, Longbing Cao, Yixuan Zhang et al.

Out-of-distribution (OOD) detection is critical for identifying test samples that deviate from in-distribution (ID) data, ensuring network robustness and reliability. This paper presents a flexible framework for OOD knowledge distillation that extracts OOD-sensitive information from a network to develop a binary classifier capable of distinguishing between ID and OOD samples in both scenarios, with and without access to training ID data. To accomplish this, we introduce Confidence Amendment (CA), an innovative methodology that transforms an OOD sample into an ID one while progressively amending prediction confidence derived from the network to enhance OOD sensitivity. This approach enables the simultaneous synthesis of both ID and OOD samples, each accompanied by an adjusted prediction confidence, thereby facilitating the training of a binary classifier sensitive to OOD. Theoretical analysis provides bounds on the generalization error of the binary classifier, demonstrating the pivotal role of confidence amendment in enhancing OOD sensitivity. Extensive experiments spanning various datasets and network architectures confirm the efficacy of the proposed method in detecting OOD samples.

Hui He, Qi Zhang, Kun Yi et al.

The non-stationary nature of real-world Multivariate Time Series (MTS) data presents forecasting models with a formidable challenge of the time-variant distribution of time series, referred to as distribution shift. Existing studies on the distribution shift mostly adhere to adaptive normalization techniques for alleviating temporal mean and covariance shifts or time-variant modeling for capturing temporal shifts. Despite improving model generalization, these normalization-based methods often assume a time-invariant transition between outputs and inputs but disregard specific intra-/inter-series correlations, while time-variant models overlook the intrinsic causes of the distribution shift. This limits model expressiveness and interpretability of tackling the distribution shift for MTS forecasting. To mitigate such a dilemma, we present a unified Probabilistic Graphical Model to Jointly capturing intra-/inter-series correlations and modeling the time-variant transitional distribution, and instantiate a neural framework called JointPGM for non-stationary MTS forecasting. Specifically, JointPGM first employs multiple Fourier basis functions to learn dynamic time factors and designs two distinct learners: intra-series and inter-series learners. The intra-series learner effectively captures temporal dynamics by utilizing temporal gates, while the inter-series learner explicitly models spatial dynamics through multi-hop propagation, incorporating Gumbel-softmax sampling. These two types of series dynamics are subsequently fused into a latent variable, which is inversely employed to infer time factors, generate final prediction, and perform reconstruction. We validate the effectiveness and efficiency of JointPGM through extensive experiments on six highly non-stationary MTS datasets, achieving state-of-the-art forecasting performance of MTS forecasting.

Zhangkai Wu, Longbing Cao

We present a self-supervised variational autoencoder (VAE) to jointly learn disentangled and dependent hidden factors and then enhance disentangled representation learning by a self-supervised classifier to eliminate coupled representations in a contrastive manner. To this end, a Contrastive Copula VAE (C$^2$VAE) is introduced without relying on prior knowledge about data in the probabilistic principle and involving strong modeling assumptions on the posterior in the neural architecture. C$^2$VAE simultaneously factorizes the posterior (evidence lower bound, ELBO) with total correlation (TC)-driven decomposition for learning factorized disentangled representations and extracts the dependencies between hidden features by a neural Gaussian copula for copula coupled representations. Then, a self-supervised contrastive classifier differentiates the disentangled representations from the coupled representations, where a contrastive loss regularizes this contrastive classification together with the TC loss for eliminating entangled factors and strengthening disentangled representations. C$^2$VAE demonstrates a strong effect in enhancing disentangled representation learning. C$^2$VAE further contributes to improved optimization addressing the TC-based VAE instability and the trade-off between reconstruction and representation.

Zhilin Zhao, Longbing Cao

Real-life data are often non-IID due to complex distributions and interactions, and the sensitivity to the distribution of samples can differ among learning models. Accordingly, a key question for any supervised or unsupervised model is whether the probability distributions of two given datasets can be considered identical. To address this question, we introduce R-divergence, designed to assess model-oriented distribution discrepancies. The core insight is that two distributions are likely identical if their optimal hypothesis yields the same expected risk for each distribution. To estimate the distribution discrepancy between two datasets, R-divergence learns a minimum hypothesis on the mixed data and then gauges the empirical risk difference between them. We evaluate the test power across various unsupervised and supervised tasks and find that R-divergence achieves state-of-the-art performance. To demonstrate the practicality of R-divergence, we employ R-divergence to train robust neural networks on samples with noisy labels.

An Lao, Qi Zhang, Chongyang Shi et al.

Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media. Existing multimodal rumor detection has focused on mixing tokens among spatial and sequential locations for unimodal representation or fusing clues of rumor veracity across modalities. However, they suffer from less discriminative unimodal representation and are vulnerable to intricate location dependencies in the time-consuming fusion of spatial and sequential tokens. This work makes the first attempt at multimodal rumor detection in the frequency domain, which efficiently transforms spatial features into the frequency spectrum and obtains highly discriminative spectrum features for multimodal representation and fusion. A novel Frequency Spectrum Representation and fUsion network (FSRU) with dual contrastive learning reveals the frequency spectrum is more effective for multimodal representation and fusion, extracting the informative components for rumor detection. FSRU involves three novel mechanisms: utilizing the Fourier transform to convert features in the spatial domain to the frequency domain, the unimodal spectrum compression, and the cross-modal spectrum co-selection module in the frequency domain. Substantial experiments show that FSRU achieves satisfactory multimodal rumor detection performance.

Jianing He, Qi Zhang, Weiping Ding et al.

Early exiting has demonstrated its effectiveness in accelerating the inference of pre-trained language models like BERT by dynamically adjusting the number of layers executed. However, most existing early exiting methods only consider local information from an individual test sample to determine their exiting indicators, failing to leverage the global information offered by sample population. This leads to suboptimal estimation of prediction correctness, resulting in erroneous exiting decisions. To bridge the gap, we explore the necessity of effectively combining both local and global information to ensure reliable early exiting during inference. Purposefully, we leverage prototypical networks to learn class prototypes and devise a distance metric between samples and class prototypes. This enables us to utilize global information for estimating the correctness of early predictions. On this basis, we propose a novel Distance-Enhanced Early Exiting framework for BERT (DE$^3$-BERT). DE$^3$-BERT implements a hybrid exiting strategy that supplements classic entropy-based local information with distance-based global information to enhance the estimation of prediction correctness for more reliable early exiting decisions. Extensive experiments on the GLUE benchmark demonstrate that DE$^3$-BERT consistently outperforms state-of-the-art models under different speed-up ratios with minimal storage or computational overhead, yielding a better trade-off between model performance and inference efficiency. Additionally, an in-depth analysis further validates the generality and interpretability of our method.

Zhangkai Wu, Xuhui Fan, Jin Li et al.

The recently proposed Bayesian Flow Networks~(BFNs) show great potential in modeling parameter spaces, offering a unified strategy for handling continuous, discretized, and discrete data. However, BFNs cannot learn high-level semantic representation from the parameter space since {common encoders, which encode data into one static representation, cannot capture semantic changes in parameters.} This motivates a new direction: learning semantic representations hidden in the parameter spaces to characterize mixed-typed noisy data. {Accordingly, we propose a representation learning framework named ParamReL, which operates in the parameter space to obtain parameter-wise latent semantics that exhibit progressive structures. Specifically, ParamReL proposes a \emph{self-}encoder to learn latent semantics directly from parameters, rather than from observations. The encoder is then integrated into BFNs, enabling representation learning with various formats of observations. Mutual information terms further promote the disentanglement of latent semantics and capture meaningful semantics simultaneously.} We illustrate {conditional generation and reconstruction} in ParamReL via expanding BFNs, and extensive {quantitative} experimental results demonstrate the {superior effectiveness} of ParamReL in learning parameter representation.

Zhangkai Wu, Longbing Cao, Qi Zhang et al.

Due to their unsupervised training and uncertainty estimation, deep Variational Autoencoders (VAEs) have become powerful tools for reconstruction-based Time Series Anomaly Detection (TSAD). Existing VAE-based TSAD methods, either statistical or deep, tune meta-priors to estimate the likelihood probability for effectively capturing spatiotemporal dependencies in the data. However, these methods confront the challenge of inherent data scarcity, which is often the case in anomaly detection tasks. Such scarcity easily leads to latent holes, discontinuous regions in latent space, resulting in non-robust reconstructions on these discontinuous spaces. We propose a novel generative framework that combines VAEs with self-supervised learning (SSL) to address this issue.

Hui Chen, Hengyu Liu, Zhangkai Wu et al.

While deep neural networks (DNNs) based personalized federated learning (PFL) is demanding for addressing data heterogeneity and shows promising performance, existing methods for federated learning (FL) suffer from efficient systematic uncertainty quantification. The Bayesian DNNs-based PFL is usually questioned of either over-simplified model structures or high computational and memory costs. In this paper, we introduce FedSI, a novel Bayesian DNNs-based subnetwork inference PFL framework. FedSI is simple and scalable by leveraging Bayesian methods to incorporate systematic uncertainties effectively. It implements a client-specific subnetwork inference mechanism, selects network parameters with large variance to be inferred through posterior distributions, and fixes the rest as deterministic ones. FedSI achieves fast and scalable inference while preserving the systematic uncertainties to the fullest extent. Extensive experiments on three different benchmark datasets demonstrate that FedSI outperforms existing Bayesian and non-Bayesian FL baselines in heterogeneous FL scenarios.

Hui Chen, Xuhui Fan, Hengyu Liu et al.

Marked event data captures events by recording their continuous-valued occurrence timestamps along with their corresponding discrete-valued types. They have appeared in various real-world scenarios such as social media, financial transactions, and healthcare records, and have been effectively modeled through Marked Temporal Point Process (MTPP) models. Recently, developing generative models for these MTPP models have seen rapid development due to their powerful generative capability and less restrictive functional forms. However, existing generative MTPP models are usually challenged in jointly modeling events' timestamps and types since: (1) mainstream methods design the generative mechanisms for timestamps only and do not include event types; (2) the complex interdependence between the timestamps and event types are overlooked. In this paper, we propose a novel generative MTPP model called BMTPP. Unlike existing generative MTPP models, BMTPP flexibly models marked temporal joint distributions using a parameter-based approach. Additionally, by adding joint noise to the marked temporal data space, BMTPP effectively captures and explicitly reveals the interdependence between timestamps and event types. Extensive experiments validate the superiority of our approach over other state-of-the-art models and its ability to effectively capture marked-temporal interdependence.

Jia Xu, Longbing Cao

We address an important yet challenging problem - modeling high-dimensional dependencies across multivariates such as financial indicators in heterogeneous markets. In reality, a market couples and influences others over time, and the financial variables of a market are also coupled. We make the first attempt to integrate variational sequential neural learning with copula-based dependence modeling to characterize both temporal observable and latent variable-based dependence degrees and structures across non-normal multivariates. Our variational neural network WPVC-VLSTM models variational sequential dependence degrees and structures across multivariate time series by variational long short-term memory networks and regular vine copula. The regular vine copula models nonnormal and long-range distributional couplings across multiple dynamic variables. WPVC-VLSTM is verified in terms of both technical significance and portfolio forecasting performance. It outperforms benchmarks including linear models, stochastic volatility models, deep neural networks, and variational recurrent networks in cross-market portfolio forecasting.

Zhilin Zhao, Longbing Cao, Yuanyu Wan

We consider a general and realistic scenario involving non-stationary time series, consisting of several offline intervals with different distributions within a fixed offline time horizon, and an online interval that continuously receives new samples. For non-stationary time series, the data distribution in the current online interval may have appeared in previous offline intervals. We theoretically explore the feasibility of applying knowledge from offline intervals to the current online interval. To this end, we propose the Mixture of Online and Offline Experts (MOOE). MOOE learns static offline experts from offline intervals and maintains a dynamic online expert for the current online interval. It then adaptively combines the offline and online experts using a meta expert to make predictions for the samples received in the online interval. Specifically, we focus on theoretical analysis, deriving parameter convergence, regret bounds, and generalization error bounds to prove the effectiveness of the algorithm.

Longbing Cao, Chengzhang Zhu

Enterprise data typically involves multiple heterogeneous data sources and external data that respectively record business activities, transactions, customer demographics, status, behaviors, interactions and communications with the enterprise, and the consumption and feedback of its products, services, production, marketing, operations, and management, etc. A critical challenge in enterprise data science is to enable an effective whole-of-enterprise data understanding and data-driven discovery and decision-making on all-round enterprise DNA. We introduce a neural encoder Table2Vec for automated universal representation learning of entities such as customers from all-round enterprise DNA with automated data characteristics analysis and data quality augmentation. The learned universal representations serve as representative and benchmarkable enterprise data genomes and can be used for enterprise-wide and domain-specific learning tasks. Table2Vec integrates automated universal representation learning on low-quality enterprise data and downstream learning tasks. We illustrate Table2Vec in characterizing all-round customer data DNA in an enterprise on complex heterogeneous multi-relational big tables to build universal customer vector representations. The learned universal representation of each customer is all-round, representative and benchmarkable to support both enterprise-wide and domain-specific learning goals and tasks in enterprise data science. Table2Vec significantly outperforms the existing shallow, boosting and deep learning methods typically used for enterprise analytics. We further discuss the research opportunities, directions and applications of automated universal enterprise representation and learning and the learned enterprise data DNA for automated, all-purpose, whole-of-enterprise and ethical machine learning and data science.

Qing Liu, Longbing Cao

The COVID-19 pandemic has posed significant challenges in modeling its complex epidemic transmissions, infection and contagion, which are very different from known epidemics. The challenges in quantifying COVID-19 complexities include effectively modeling its process and data uncertainties. The uncertainties are embedded in implicit and high-proportional undocumented infections, asymptomatic contagion, social reinforcement of infections, and various quality issues in the reported data. These uncertainties become even more apparent in the first two months of the COVID-19 pandemic, when the relevant knowledge, case reporting and testing were all limited. Here we introduce a novel hybrid approach Susceptible-Undocumented infected-Documented infected-Recovered (SUDR) model. First, SUDR (1) characterizes and distinguishes Undocumented (U) and Documented (D) infections commonly seen during COVID-19 incubation periods and asymptomatic infections. Second, SUDR characterizes the probabilistic density of infections by capturing exogenous processes. Lastly, SUDR approximates the density likelihood of COVID-19 prevalence over time by incorporating Bayesian inference into SUDR. Different from existing COVID-19 models, SUDR characterizes the undocumented infections during unknown transmission processes. To capture the uncertainties of temporal transmission and social reinforcement during COVID-19 contagion, the transmission rate is modeled by a time-varying density function of undocumented infectious cases. By sampling from the mean-field posterior distribution with reasonable priors, SUDR handles the randomness, noise and sparsity of COVID-19 observations widely seen in the public COVID-19 case data. The results demonstrate a deeper quantitative understanding of the above uncertainties, in comparison with classic SIR, time-dependent SIR, and probabilistic SIR models.

Zhilin Zhao, Longbing Cao, Kun-Yu Lin

In deep neural learning, a discriminator trained on in-distribution (ID) samples may make high-confidence predictions on out-of-distribution (OOD) samples. This triggers a significant matter for robust, trustworthy and safe deep learning. The issue is primarily caused by the limited ID samples observable in training the discriminator when OOD samples are unavailable. We propose a general approach for \textit{fine-tuning discriminators by implicit generators} (FIG). FIG is grounded on information theory and applicable to standard discriminators without retraining. It improves the ability of a standard discriminator in distinguishing ID and OOD samples by generating and penalizing its specific OOD samples. According to the Shannon entropy, an energy-based implicit generator is inferred from a discriminator without extra training costs. Then, a Langevin dynamic sampler draws specific OOD samples for the implicit generator. Lastly, we design a regularizer fitting the design principle of the implicit generator to induce high entropy on those generated OOD samples. The experiments on different networks and datasets demonstrate that FIG achieves the state-of-the-art OOD detection performance.

Longbing Cao, Chengzhang Zhu

Automated next-best action recommendation for each customer in a sequential, dynamic and interactive context has been widely needed in natural, social and business decision-making. Personalized next-best action recommendation must involve past, current and future customer demographics and circumstances (states) and behaviors, long-range sequential interactions between customers and decision-makers, multi-sequence interactions between states, behaviors and actions, and their reactions to their counterpart's actions. No existing modeling theories and tools, including Markovian decision processes, user and behavior modeling, deep sequential modeling, and personalized sequential recommendation, can quantify such complex decision-making on a personal level. We take a data-driven approach to learn the next-best actions for personalized decision-making by a reinforced coupled recurrent neural network (CRN). CRN represents multiple coupled dynamic sequences of a customer's historical and current states, responses to decision-makers' actions, decision rewards to actions, and learns long-term multi-sequence interactions between parties (customer and decision-maker). Next-best actions are then recommended on each customer at a time point to change their state for an optimal decision-making objective. Our study demonstrates the potential of personalized deep learning of multi-sequence interactions and automated dynamic intervention for personalized decision-making in complex systems.

Siyuan Ren, Bin Guo, Longbing Cao et al.

The prediction of express delivery sequence, i.e., modeling and estimating the volumes of daily incoming and outgoing parcels for delivery, is critical for online business, logistics, and positive customer experience, and specifically for resource allocation optimization and promotional activity arrangement. A precise estimate of consumer delivery requests has to involve sequential factors such as shopping behaviors, weather conditions, events, business campaigns, and their couplings. Besides, conventional sequence prediction assumes a stable sequence evolution, failing to address complex nonlinear sequences and various feature effects in the above multi-source data. Although deep networks and attention mechanisms demonstrate the potential of complex sequence modeling, extant networks ignore the heterogeneous and coupling situation between features and sequences, resulting in weak prediction accuracy. To address these issues, we propose DeepExpress - a deep-learning based express delivery sequence prediction model, which extends the classic seq2seq framework to learning complex coupling between sequence and features. DeepExpress leverages an express delivery seq2seq learning, a carefully-designed heterogeneous feature representation, and a novel joint training attention mechanism to adaptively map heterogeneous data, and capture sequence-feature coupling for precise estimation. Experimental results on real-world data demonstrate that the proposed method outperforms both shallow and deep baseline models.

Longbing Cao

AI in finance broadly refers to the applications of AI techniques in financial businesses. This area has been lasting for decades with both classic and modern AI techniques applied to increasingly broader areas of finance, economy and society. In contrast to either discussing the problems, aspects and opportunities of finance that have benefited from specific AI techniques and in particular some new-generation AI and data science (AIDS) areas or reviewing the progress of applying specific techniques to resolving certain financial problems, this review offers a comprehensive and dense roadmap of the overwhelming challenges, techniques and opportunities of AI research in finance over the past decades. The landscapes and challenges of financial businesses and data are firstly outlined, followed by a comprehensive categorization and a dense overview of the decades of AI research in finance. We then structure and illustrate the data-driven analytics and learning of financial businesses and data. The comparison, criticism and discussion of classic vs. modern AI techniques for finance are followed. Lastly, open issues and opportunities address future AI-empowered finance and finance-motivated AI research.

Jinjin Guo, Longbing Cao, Zhiguo Gong

The abundant sequential documents such as online archival, social media and news feeds are streamingly updated, where each chunk of documents is incorporated with smoothly evolving yet dependent topics. Such digital texts have attracted extensive research on dynamic topic modeling to infer hidden evolving topics and their temporal dependencies. However, most of the existing approaches focus on single-topic-thread evolution and ignore the fact that a current topic may be coupled with multiple relevant prior topics. In addition, these approaches also incur the intractable inference problem when inferring latent parameters, resulting in a high computational cost and performance degradation. In this work, we assume that a current topic evolves from all prior topics with corresponding coupling weights, forming the multi-topic-thread evolution. Our method models the dependencies between evolving topics and thoroughly encodes their complex multi-couplings across time steps. To conquer the intractable inference challenge, a new solution with a set of novel data augmentation techniques is proposed, which successfully discomposes the multi-couplings between evolving topics. A fully conjugate model is thus obtained to guarantee the effectiveness and efficiency of the inference technique. A novel Gibbs sampler with a backward-forward filter algorithm efficiently learns latent timeevolving parameters in a closed-form. In addition, the latent Indian Buffet Process (IBP) compound distribution is exploited to automatically infer the overall topic number and customize the sparse topic proportions for each sequential document without bias. The proposed method is evaluated on both synthetic and real-world datasets against the competitive baselines, demonstrating its superiority over the baselines in terms of the low per-word perplexity, high coherent topics, and better document time prediction.

Shoujin Wang, Liang Hu, Yan Wang et al.

Recent years have witnessed the fast development of the emerging topic of Graph Learning based Recommender Systems (GLRS). GLRS employ advanced graph learning approaches to model users' preferences and intentions as well as items' characteristics for recommendations. Differently from other RS approaches, including content-based filtering and collaborative filtering, GLRS are built on graphs where the important objects, e.g., users, items, and attributes, are either explicitly or implicitly connected. With the rapid development of graph learning techniques, exploring and exploiting homogeneous or heterogeneous relations in graphs are a promising direction for building more effective RS. In this paper, we provide a systematic review of GLRS, by discussing how they extract important knowledge from graph-based representations to improve the accuracy, reliability and explainability of the recommendations. First, we characterize and formalize GLRS, and then summarize and categorize the key challenges and main progress in this novel research area. Finally, we share some new research directions in this vibrant area.

Longbing Cao, Qing Liu

The SARS-CoV-2 virus and COVID-19 disease have posed unprecedented and overwhelming demand, challenges and opportunities to domain, model and data driven modeling. This paper provides a comprehensive review of the challenges, tasks, methods, progress, gaps and opportunities in relation to modeling COVID-19 problems, data and objectives. It constructs a research landscape of COVID-19 modeling tasks and methods, and further categorizes, summarizes, compares and discusses the related methods and progress of modeling COVID-19 epidemic transmission processes and dynamics, case identification and tracing, infection diagnosis and medical treatments, non-pharmaceutical interventions and their effects, drug and vaccine development, psychological, economic and social influence and impact, and misinformation, etc. The modeling methods involve mathematical and statistical models, domain-driven modeling by epidemiological compartmental models, medical and biomedical analysis, AI and data science in particular shallow and deep machine learning, simulation modeling, social science methods, and hybrid modeling.

Guansong Pang, Longbing Cao, Ling Chen

Most of existing outlier detection methods assume that the outlier factors (i.e., outlierness scoring measures) of data entities (e.g., feature values and data objects) are Independent and Identically Distributed (IID). This assumption does not hold in real-world applications where the outlierness of different entities is dependent on each other and/or taken from different probability distributions (non-IID). This may lead to the failure of detecting important outliers that are too subtle to be identified without considering the non-IID nature. The issue is even intensified in more challenging contexts, e.g., high-dimensional data with many noisy features. This work introduces a novel outlier detection framework and its two instances to identify outliers in categorical data by capturing non-IID outlier factors. Our approach first defines and incorporates distribution-sensitive outlier factors and their interdependence into a value-value graph-based representation. It then models an outlierness propagation process in the value graph to learn the outlierness of feature values. The learned value outlierness allows for either direct outlier detection or outlying feature selection. The graph representation and mining approach is employed here to well capture the rich non-IID characteristics. Our empirical results on 15 real-world data sets with different levels of data complexities show that (i) the proposed outlier detection methods significantly outperform five state-of-the-art methods at the 95%/99% confidence level, achieving 10%-28% AUC improvement on the 10 most complex data sets; and (ii) the proposed feature selection methods significantly outperform three competing methods in enabling subsequent outlier detection of two different existing detectors.

Guansong Pang, Anton van den Hengel, Chunhua Shen et al.

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data. We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies. This approach learns the known abnormality by automatically interacting with an anomaly-biased simulation environment, while continuously extending the learned abnormality to novel classes of anomaly (i.e., unknown anomalies) by actively exploring possible anomalies in the unlabeled data. This is achieved by jointly optimizing the exploitation of the small labeled anomaly data and the exploration of the rare unlabeled anomalies. Extensive experiments on 48 real-world datasets show that our model significantly outperforms five state-of-the-art competing methods.

Chengzhang Zhu, Longbing Cao, Jianping Yin

Complex categorical data is often hierarchically coupled with heterogeneous relationships between attributes and attribute values and the couplings between objects. Such value-to-object couplings are heterogeneous with complementary and inconsistent interactions and distributions. Limited research exists on unlabeled categorical data representations, ignores the heterogeneous and hierarchical couplings, underestimates data characteristics and complexities, and overuses redundant information, etc. The deep representation learning of unlabeled categorical data is challenging, overseeing such value-to-object couplings, complementarity and inconsistency, and requiring large data, disentanglement, and high computational power. This work introduces a shallow but powerful UNsupervised heTerogeneous couplIng lEarning (UNTIE) approach for representing coupled categorical data by untying the interactions between couplings and revealing heterogeneous distributions embedded in each type of couplings. UNTIE is efficiently optimized w.r.t. a kernel k-means objective function for unsupervised representation learning of heterogeneous and hierarchical value-to-object couplings. Theoretical analysis shows that UNTIE can represent categorical data with maximal separability while effectively represent heterogeneous couplings and disclose their roles in categorical data. The UNTIE-learned representations make significant performance improvement against the state-of-the-art categorical representations and deep representation models on 25 categorical data sets with diversified characteristics.

Longbing Cao, Qiang Yang, Philip S. Yu

Financial technology (FinTech) has been playing an increasingly critical role in driving modern economies, society, technology, and many other areas. Smart FinTech is the new-generation FinTech, largely inspired and empowered by data science and new-generation AI and (DSAI) techniques. Smart FinTech synthesizes broad DSAI and transforms finance and economies to drive intelligent, automated, whole-of-business and personalized economic and financial businesses, services and systems. The research on data science and AI in FinTech involves many latest progress made in smart FinTech for BankingTech, TradeTech, LendTech, InsurTech, WealthTech, PayTech, RiskTech, cryptocurrencies, and blockchain, and the DSAI techniques including complex system methods, quantitative methods, intelligent interactions, recognition and responses, data analytics, deep learning, federated learning, privacy-preserving processing, augmentation, optimization, and system intelligence enhancement. Here, we present a highly dense research overview of smart financial businesses and their challenges, the smart FinTech ecosystem, the DSAI techniques to enable smart FinTech, and some research directions of smart FinTech futures to the DSAI communities.

Longbing Cao

Complex applications such as big data analytics involve different forms of coupling relationships that reflect interactions between factors related to technical, business (domain-specific) and environmental (including socio-cultural and economic) aspects. There are diverse forms of couplings embedded in poor-structured and ill-structured data. Such couplings are ubiquitous, implicit and/or explicit, objective and/or subjective, heterogeneous and/or homogeneous, presenting complexities to existing learning systems in statistics, mathematics and computer sciences, such as typical dependency, association and correlation relationships. Modeling and learning such couplings thus is fundamental but challenging. This paper discusses the concept of coupling learning, focusing on the involvement of coupling relationships in learning systems. Coupling learning has great potential for building a deep understanding of the essence of business problems and handling challenges that have not been addressed well by existing learning theories and tools. This argument is verified by several case studies on coupling learning, including handling coupling in recommender systems, incorporating couplings into coupled clustering, coupling document clustering, coupled recommender algorithms and coupled behavior analysis for groups.

Shoujin Wang, Longbing Cao, Liang Hu et al.

A transaction-based recommender system (TBRS) aims to predict the next item by modeling dependencies in transactional data. Generally, two kinds of dependencies considered are intra-transaction dependency and inter-transaction dependency. Most existing TBRSs recommend next item by only modeling the intra-transaction dependency within the current transaction while ignoring inter-transaction dependency with recent transactions that may also affect the next item. However, as not all recent transactions are relevant to the current and next items, the relevant ones should be identified and prioritized. In this paper, we propose a novel hierarchical attentive transaction embedding (HATE) model to tackle these issues. Specifically, a two-level attention mechanism integrates both item embedding and transaction embedding to build an attentive context representation that incorporates both intraand inter-transaction dependencies. With the learned context representation, HATE then recommends the next item. Experimental evaluations on two real-world transaction datasets show that HATE significantly outperforms the state-ofthe-art methods in terms of recommendation accuracy.

Shoujin Wang, Liang Hu, Yan Wang et al.

Recent years have witnessed the fast development of the emerging topic of Graph Learning based Recommender Systems (GLRS). GLRS mainly employ the advanced graph learning approaches to model users' preferences and intentions as well as items' characteristics and popularity for Recommender Systems (RS). Differently from conventional RS, including content based filtering and collaborative filtering, GLRS are built on simple or complex graphs where various objects, e.g., users, items, and attributes, are explicitly or implicitly connected. With the rapid development of graph learning, exploring and exploiting homogeneous or heterogeneous relations in graphs is a promising direction for building advanced RS. In this paper, we provide a systematic review of GLRS, on how they obtain the knowledge from graphs to improve the accuracy, reliability and explainability for recommendations. First, we characterize and formalize GLRS, and then summarize and categorize the key challenges in this new research area. Then, we survey the most recent and important developments in the area. Finally, we share some new research directions in this vibrant area.

Longxiang Shi, Shijian Li, Longbing Cao et al.

In recent years significant progress has been made in dealing with challenging problems using reinforcement learning.Despite its great success, reinforcement learning still faces challenge in continuous control tasks. Conventional methods always compute the derivatives of the optimal goal with a costly computation resources, and are inefficient, unstable and lack of robust-ness when dealing with such tasks. Alternatively, derivative-based methods treat the optimization process as a blackbox and show robustness and stability in learning continuous control tasks, but not data efficient in learning. The combination of both methods so as to get the best of the both has raised attention. However, most of the existing combination works adopt complex neural networks (NNs) as the policy for control. The double-edged sword of deep NNs can yield better performance, but also makes it difficult for parameter tuning and computation. To this end, in this paper we presents a novel method called FiDi-RL, which incorporates deep RL with Finite-Difference (FiDi) policy search.FiDi-RL combines Deep Deterministic Policy Gradients (DDPG)with Augment Random Search (ARS) and aims at improving the data efficiency of ARS. The empirical results show that FiDi-RL can improves the performance and stability of ARS, and provide competitive results against some existing deep reinforcement learning methods

Peng Xu, Zhaohong Deng, Kup-Sze Choi et al.

Multi-view clustering has received much attention recently. Most of the existing multi-view clustering methods only focus on one-sided clustering. As the co-occurring data elements involve the counts of sample-feature co-occurrences, it is more efficient to conduct two-sided clustering along the samples and features simultaneously. To take advantage of two-sided clustering for the co-occurrences in the scene of multi-view clustering, a two-sided multi-view clustering method is proposed, i.e., multi-view information-theoretic co-clustering (MV-ITCC). The proposed method realizes two-sided clustering for co-occurring multi-view data under the formulation of information theory. More specifically, it exploits the agreement and disagreement among views by sharing a common clustering results along the sample dimension and keeping the clustering results of each view specific along the feature dimension. In addition, the mechanism of maximum entropy is also adopted to control the importance of different views, which can give a right balance in leveraging the agreement and disagreement. Extensive experiments are conducted on text and image multi-view datasets. The results clearly demonstrate the superiority of the proposed method.

Longxiang Shi, Shijian Li, Longbing Cao et al.

Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way, such as importance sampling and tree-backup. However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems. The traces are cut immediately when a non-greedy action is taken, which may lose the advantage of eligibility traces and slow down the learning process. Alternatively, some non-probabilistic measurement methods such as General Q($λ$) and Naive Q($λ$) never cut traces, but face convergence problems in practice. To address the above issues, this paper introduces a new method named TBQ($σ$), which effectively unifies the tree-backup algorithm and Naive Q($λ$). By introducing a new parameter $σ$ to illustrate the \emph{degree} of utilizing traces, TBQ($σ$) creates an effective integration of TB($λ$) and Naive Q($λ$) and continuous role shift between them. The contraction property of TB($σ$) is theoretically analyzed for both policy evaluation and control settings. We also derive the online version of TBQ($σ$) and give the convergence proof. We empirically show that, for $ε\in(0,1]$ in $ε$-greedy policies, there exists some degree of utilizing traces for $λ\in[0,1]$, which can improve the efficiency in trace utilization for off-policy reinforcement learning, to both accelerate the learning process and improve the performance.

Shoujin Wang, Longbing Cao, Yan Wang et al.

Recommender systems (RSs) have been playing an increasingly important role for informed consumption, services, and decision-making in the overloaded information era and digitized economy. In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs. Different from other RSs such as content-based RSs and collaborative filtering-based RSs which usually model long-term yet static user preferences, SBRSs aim to capture short-term but dynamic user preferences to provide more timely and accurate recommendations sensitive to the evolution of their session contexts. Although SBRSs have been intensively studied, neither unified problem statements for SBRSs nor in-depth elaboration of SBRS characteristics and challenges are available. It is also unclear to what extent SBRS challenges have been addressed and what the overall research landscape of SBRSs is. This comprehensive review of SBRSs addresses the above aspects by exploring in depth the SBRS entities (e.g., sessions), behaviours (e.g., users' clicks on items) and their properties (e.g., session length). We propose a general problem statement of SBRSs, summarize the diversified data characteristics and challenges of SBRSs, and define a taxonomy to categorize the representative SBRS research. Finally, we discuss new research opportunities in this exciting and vibrant area.

Guansong Pang, Longbing Cao, Ling Chen et al.

Learning expressive low-dimensional representations of ultrahigh-dimensional data, e.g., data with thousands/millions of features, has been a major way to enable learning methods to address the curse of dimensionality. However, existing unsupervised representation learning methods mainly focus on preserving the data regularity information and learning the representations independently of subsequent outlier detection methods, which can result in suboptimal and unstable performance of detecting irregularities (i.e., outliers). This paper introduces a ranking model-based framework, called RAMODO, to address this issue. RAMODO unifies representation learning and outlier detection to learn low-dimensional representations that are tailored for a state-of-the-art outlier detection approach - the random distance-based approach. This customized learning yields more optimal and stable representations for the targeted outlier detectors. Additionally, RAMODO can leverage little labeled data as prior knowledge to learn more expressive and application-relevant representations. We instantiate RAMODO to an efficient method called REPEN to demonstrate the performance of RAMODO. Extensive empirical results on eight real-world ultrahigh dimensional data sets show that REPEN (i) enables a random distance-based detector to obtain significantly better AUC performance and two orders of magnitude speedup; (ii) performs substantially better and more stably than four state-of-the-art representation learning methods; and (iii) leverages less than 1% labeled data to achieve up to 32% AUC improvement.

Fangfang Li, Guandong Xu, Longbing Cao

Supervised classification approaches can predict labels for unknown data because of the supervised training process. The success of classification is heavily dependent on the labeled training data. Differently, clustering is effective in revealing the aggregation property of unlabeled data, but the performance of most clustering methods is limited by the absence of labeled data. In real applications, however, it is time-consuming and sometimes impossible to obtain labeled data. The combination of clustering and classification is a promising and active approach which can largely improve the performance. In this paper, we propose an innovative and effective clustering framework based on self-adaptive labeling (CSAL) which integrates clustering and classification on unlabeled data. Clustering is first employed to partition data and a certain proportion of clustered data are selected by our proposed labeling approach for training classifiers. In order to refine the trained classifiers, an iterative process of Expectation-Maximization algorithm is devised into the proposed clustering framework CSAL. Experiments are conducted on publicly data sets to test different combinations of clustering algorithms and classification models as well as various training data labeling methods. The experimental results show that our approach along with the self-adaptive method outperforms other methods.