Can Wang

Zhiyao Zhou, Sheng Zhou, Bochao Mao et al.

Graph Neural Networks (GNNs) have emerged as the de facto standard for representation learning on graphs, owing to their ability to effectively integrate graph topology and node attributes. However, the inherent suboptimal nature of node connections, resulting from the complex and contingent formation process of graphs, presents significant challenges in modeling them effectively. To tackle this issue, Graph Structure Learning (GSL), a family of data-centric learning approaches, has garnered substantial attention in recent years. The core concept behind GSL is to jointly optimize the graph structure and the corresponding GNN models. Despite the proposal of numerous GSL methods, the progress in this field remains unclear due to inconsistent experimental protocols, including variations in datasets, data processing techniques, and splitting strategies. In this paper, we introduce OpenGSL, the first comprehensive benchmark for GSL, aimed at addressing this gap. OpenGSL enables a fair comparison among state-of-the-art GSL methods by evaluating them across various popular datasets using uniform data processing and splitting strategies. Through extensive experiments, we observe that existing GSL methods do not consistently outperform vanilla GNN counterparts. We also find that there is no significant correlation between the homophily of the learned structure and task performance, challenging the common belief. Moreover, we observe that the learned graph structure demonstrates a strong generalization ability across different GNN models, despite the high computational and space consumption. We hope that our open-sourced library will facilitate rapid and equitable evaluation and inspire further innovative research in this field. The code of the benchmark can be found in https://github.com/OpenGSL/OpenGSL.

Zhenyu Zhou, Defang Chen, Can Wang et al.

Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs), with the aim of obtaining an accurate solution with as few number of function evaluations (NFE) as possible. Recently, various fast samplers utilizing higher-order ODE solvers have emerged and achieved better performance than the initial first-order one. However, these numerical methods inherently result in certain approximation errors, which significantly degrades sample quality with extremely small NFE (e.g., around 5). In contrast, based on the geometric observation that each sampling trajectory almost lies in a two-dimensional subspace embedded in the ambient space, we propose Approximate MEan-Direction Solver (AMED-Solver) that eliminates truncation errors by directly learning the mean direction for fast diffusion sampling. Besides, our method can be easily used as a plugin to further improve existing ODE-based samplers. Extensive experiments on image synthesis with the resolution ranging from 32 to 512 demonstrate the effectiveness of our method. With only 5 NFE, we achieve 6.61 FID on CIFAR-10, 10.74 FID on ImageNet 64$\times$64, and 13.20 FID on LSUN Bedroom. Our code is available at https://github.com/zju-pi/diff-sampler.

Hailin Zhang, Defang Chen, Can Wang

Multi-Teacher knowledge distillation provides students with additional supervision from multiple pre-trained teachers with diverse information sources. Most existing methods explore different weighting strategies to obtain a powerful ensemble teacher, while ignoring the student with poor learning ability may not benefit from such specialized integrated knowledge. To address this problem, we propose Adaptive Multi-teacher Knowledge Distillation with Meta-Learning (MMKD) to supervise student with appropriate knowledge from a tailored ensemble teacher. With the help of a meta-weight network, the diverse yet compatible teacher knowledge in the output layer and intermediate layers is jointly leveraged to enhance the student performance. Extensive experiments on multiple benchmark datasets validate the effectiveness and flexibility of our methods. Code is available: https://github.com/Rorozhl/MMKD.

Defang Chen, Jian-Ping Mei, Hailin Zhang et al.

Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years, generally with elaborately designed knowledge representations, which in turn increase the difficulty of model development and interpretation. In contrast, we empirically show that a simple knowledge distillation technique is enough to significantly narrow down the teacher-student performance gap. We directly reuse the discriminative classifier from the pre-trained teacher model for student inference and train a student encoder through feature alignment with a single $\ell_2$ loss. In this way, the student model is able to achieve exactly the same performance as the teacher model provided that their extracted features are perfectly aligned. An additional projector is developed to help the student encoder match with the teacher classifier, which renders our technique applicable to various teacher and student architectures. Extensive experiments demonstrate that our technique achieves state-of-the-art results at the modest cost of compression ratio due to the added projector.

Jiongyu Guo, Defang Chen, Can Wang

Existing knowledge distillation methods on graph neural networks (GNNs) are almost offline, where the student model extracts knowledge from a powerful teacher model to improve its performance. However, a pre-trained teacher model is not always accessible due to training cost, privacy, etc. In this paper, we propose a novel online knowledge distillation framework to resolve this problem. Specifically, each student GNN model learns the extracted local structure from another simultaneously trained counterpart in an alternating training procedure. We further develop a cross-layer distillation strategy by aligning ahead one student layer with the layer in different depth of another student model, which theoretically makes the structure information spread over all layers. Experimental results on five datasets including PPI, Coauthor-CS/Physics and Amazon-Computer/Photo demonstrate that the student performance is consistently boosted in our collaborative training framework without the supervision of a pre-trained teacher model. In addition, we also find that our alignahead technique can accelerate the model convergence speed and its effectiveness can be generally improved by increasing the student numbers in training. Code is available: https://github.com/GuoJY-eatsTG/Alignahead

Shiya Luo, Defang Chen, Can Wang

Data-free knowledge distillation (DFKD) aims to obtain a lightweight student model without original training data. Existing works generally synthesize data from the pre-trained teacher model to replace the original training data for student learning. To more effectively train the student model, the synthetic data shall be customized to the current student learning ability. However, this is ignored in the existing DFKD methods and thus negatively affects the student training. To address this issue, we propose Customizing Synthetic Data for Data-Free Student Learning (CSD) in this paper, which achieves adaptive data synthesis using a self-supervised augmented auxiliary task to estimate the student learning ability. Specifically, data synthesis is dynamically adjusted to enlarge the cross entropy between the labels and the predictions from the self-supervised augmented task, thus generating hard samples for the student model. The experiments on various datasets and teacher-student models show the effectiveness of our proposed method. Code is available at: $\href{https://github.com/luoshiya/CSD}{https://github.com/luoshiya/CSD}$

ZiJie Song, JiaWei Chen, Sheng Zhou et al.

In recommendation systems (RS), user behavior data is observational rather than experimental, resulting in widespread bias in the data. Consequently, tackling bias has emerged as a major challenge in the field of recommendation systems. Recently, Doubly Robust Learning (DR) has gained significant attention due to its remarkable performance and robust properties. However, our experimental findings indicate that existing DR methods are severely impacted by the presence of so-called Poisonous Imputation, where the imputation significantly deviates from the truth and becomes counterproductive. To address this issue, this work proposes Conservative Doubly Robust strategy (CDR) which filters imputations by scrutinizing their mean and variance. Theoretical analyses show that CDR offers reduced variance and improved tail bounds.In addition, our experimental investigations illustrate that CDR significantly enhances performance and can indeed reduce the frequency of poisonous imputation.

Yichen Liu, Jiawei Chen, Defang Chen et al.

Knowledge Graph Embedding (KGE), which projects entities and relations into continuous vector spaces, has garnered significant attention. Although high-dimensional KGE methods offer better performance, they come at the expense of significant computation and memory overheads. Decreasing embedding dimensions significantly deteriorates model performance. While several recent efforts utilize knowledge distillation or non-Euclidean representation learning to augment the effectiveness of low-dimensional KGE, they either necessitate a pre-trained high-dimensional teacher model or involve complex non-Euclidean operations, thereby incurring considerable additional computational costs. To address this, this work proposes Confidence-aware Self-Knowledge Distillation (CSD) that learns from the model itself to enhance KGE in a low-dimensional space. Specifically, CSD extracts knowledge from embeddings in previous iterations, which would be utilized to supervise the learning of the model in the next iterations. Moreover, a specific semantic module is developed to filter reliable knowledge by estimating the confidence of previously learned embeddings. This straightforward strategy bypasses the need for time-consuming pre-training of teacher models and can be integrated into various KGE methods to improve their performance. Our comprehensive experiments on six KGE backbones and four datasets underscore the effectiveness of the proposed CSD.

Bohao Wang, Feng Liu, Changwang Zhang et al.

Sequential Recommenders generate recommendations based on users' historical interaction sequences. However, in practice, these collected sequences are often contaminated by noisy interactions, which significantly impairs recommendation performance. Accurately identifying such noisy interactions without additional information is particularly challenging due to the absence of explicit supervisory signals indicating noise. Large Language Models (LLMs), equipped with extensive open knowledge and semantic reasoning abilities, offer a promising avenue to bridge this information gap. However, employing LLMs for denoising in sequential recommendation presents notable challenges: 1) Direct application of pretrained LLMs may not be competent for the denoising task, frequently generating nonsensical responses; 2) Even after fine-tuning, the reliability of LLM outputs remains questionable, especially given the complexity of the denoising task and the inherent hallucinatory issue of LLMs. To tackle these challenges, we propose LLM4DSR, a tailored approach for denoising sequential recommendation using LLMs. We constructed a self-supervised fine-tuning task to activate LLMs' capabilities to identify noisy items and suggest replacements. Furthermore, we developed an uncertainty estimation module that ensures only high-confidence responses are utilized for sequence corrections. Remarkably, LLM4DSR is model-agnostic, allowing corrected sequences to be flexibly applied across various recommendation models. Extensive experiments validate the superiority of LLM4DSR over existing methods.

Qihao Shi, Wenjie Tian, Wujian Yang et al.

In this paper, we propose a new influence spread model, namely, Complementary\&Competitive Independent Cascade (C$^2$IC) model. C$^2$IC model generalizes three well known influence model, i.e., influence boosting (IB) model, campaign oblivious (CO)IC model and the IC-N (IC model with negative opinions) model. This is the first model that considers both complementary and competitive influence spread comprehensively under multi-agent environment. Correspondingly, we propose the Complementary\&Competitive influence maximization (C$^2$IM) problem. Given an ally seed set and a rival seed set, the C$^2$IM problem aims to select a set of assistant nodes that can boost the ally spread and prevent the rival spread concurrently. We show the problem is NP-hard and can generalize the influence boosting problem and the influence blocking problem. With classifying the different cascade priorities into 4 cases by the monotonicity and submodularity (M\&S) holding conditions, we design 4 algorithms respectively, with theoretical approximation bounds provided. We conduct extensive experiments on real social networks and the experimental results demonstrate the effectiveness of the proposed algorithms. We hope this work can inspire abundant future exploration for constructing more generalized influence models that help streamline the works of this area.

Qihao Shi, Bingyang Fu, Can Wang et al.

In this paper, we study the \underline{R}obust \underline{o}ptimization for \underline{se}quence \underline{Net}worked \underline{s}ubmodular maximization (RoseNets) problem. We interweave the robust optimization with the sequence networked submodular maximization. The elements are connected by a directed acyclic graph and the objective function is not submodular on the elements but on the edges in the graph. Under such networked submodular scenario, the impact of removing an element from a sequence depends both on its position in the sequence and in the network. This makes the existing robust algorithms inapplicable. In this paper, we take the first step to study the RoseNets problem. We design a robust greedy algorithm, which is robust against the removal of an arbitrary subset of the selected elements. The approximation ratio of the algorithm depends both on the number of the removed elements and the network topology. We further conduct experiments on real applications of recommendation and link prediction. The experimental results demonstrate the effectiveness of the proposed algorithm.

Jiongyu Guo, Defang Chen, Can Wang

Graph neural networks (GNNs) have become one of the most popular research topics in both academia and industry communities for their strong ability in handling irregular graph data. However, large-scale datasets are posing great challenges for deploying GNNs in edge devices with limited resources and model compression techniques have drawn considerable research attention. Existing model compression techniques such as knowledge distillation (KD) mainly focus on convolutional neural networks (CNNs). Only limited attempts have been made recently for distilling knowledge from GNNs in an offline manner. As the performance of the teacher model does not necessarily improve as the number of layers increases in GNNs, selecting an appropriate teacher model will require substantial efforts. To address these challenges, we propose a novel online knowledge distillation framework called Alignahead++ in this paper. Alignahead++ transfers structure and feature information in a student layer to the previous layer of another simultaneously trained student model in an alternating training procedure. Meanwhile, to avoid over-smoothing problem in GNNs, deep supervision is employed in Alignahead++ by adding an auxiliary classifier in each intermediate layer to prevent the collapse of the node feature embeddings. Experimental results on four datasets including PPI, Cora, PubMed and CiteSeer demonstrate that the student performance is consistently boosted in our collaborative training framework without the supervision of a pre-trained teacher model and its effectiveness can generally be improved by increasing the number of students.

Shengjia Zhang, Junjie Wu, Jiawei Chen et al.

Recent advanced large reasoning models (LRMs) leverage extended chain-of-thought (CoT) reasoning to solve complex tasks, achieving state-of-the-art performance. Despite their success, we identify a critical issue: a substantial portion of simple tasks solved by LRMs can also be addressed by non-reasoning LLMs using significantly fewer tokens, indicating the complex reasoning may not always be necessary. To address this, we systematically analyze the reasoning trajectories of LRMs and present a method utilizing identified paradigms and LLM-Judge to classify these trajectories as either Redundant Reasoning or Essential Reasoning. And we introduce OThink-R1, a method that prunes redundant reasoning steps while preserving logical validity. OThink-R1 dynamically employs the non-thinking mode (fast-thinking) for straightforward problems while engaging in deliberate thinking (slow-thinking) for complex problems. Experiments across mathematical and question-answering tasks demonstrate that OThink-R1 reduces reasoning redundancy by almost 23\% on average without compromising accuracy, offering practical guidelines for efficient reasoning models. The code is available at https://github.com/AgenticIR-Lab/OThink-R1.

Defang Chen, Zhenyu Zhou, Jian-Ping Mei et al.

Recent years have witnessed significant progress in developing effective training and fast sampling techniques for diffusion models. A remarkable advancement is the use of stochastic differential equations (SDEs) and their marginal-preserving ordinary differential equations (ODEs) to describe data perturbation and generative modeling in a unified framework. In this paper, we carefully inspect the ODE-based sampling of a popular variance-exploding SDE and reveal several intriguing structures of its sampling dynamics. We discover that the data distribution and the noise distribution are smoothly connected with a quasi-linear sampling trajectory and another implicit denoising trajectory that even converges faster. Meanwhile, the denoising trajectory governs the curvature of the corresponding sampling trajectory and its finite differences yield various second-order samplers used in practice. Furthermore, we establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm, with which we can characterize the asymptotic behavior of diffusion models and identify the empirical score deviation. Code is available at \url{https://github.com/zju-pi/diff-sampler}.

Shiya Luo, Defang Chen, Can Wang

Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only used to provide the supervisory signal for the last layer of the student model, which may result in those shallow student layers lacking accurate training guidance in the layer-by-layer back propagation and thus hinders effective knowledge transfer. To address this issue, we propose Deeply-Supervised Knowledge Distillation (DSKD), which fully utilizes class predictions and feature maps of the teacher model to supervise the training of shallow student layers. A loss-based weight allocation strategy is developed in DSKD to adaptively balance the learning process of each shallow layer, so as to further improve the student performance. Extensive experiments on CIFAR-100 and TinyImageNet with various teacher-student models show significantly performance, confirming the effectiveness of our proposed method. Code is available at: $\href{https://github.com/luoshiya/DSKD}{https://github.com/luoshiya/DSKD}$

Can Wang, Zhe Wang, Defang Chen et al.

Knowledge distillation, a technique recently gaining popularity for enhancing model generalization in Convolutional Neural Networks (CNNs), operates under the assumption that both teacher and student models are trained on identical data distributions. However, its effect on Graph Neural Networks (GNNs) is less than satisfactory since the graph topology and node attributes are prone to evolve, thereby leading to the issue of distribution shift. In this paper, we tackle this challenge by simultaneously training a group of graph neural networks in an online distillation fashion, where the group knowledge plays a role as a dynamic virtual teacher and the structure changes in graph neural networks are effectively captured. To improve the distillation performance, two types of knowledge are transferred among the students to enhance each other: local knowledge reflecting information in the graph topology and node attributes, and global knowledge reflecting the prediction over classes. We transfer the global knowledge with KL-divergence as the vanilla knowledge distillation does, while exploiting the complicated structure of the local knowledge with an efficient adversarial cyclic learning framework. Extensive experiments verified the effectiveness of our proposed online adversarial distillation approach. The code is published at https://github.com/wangz3066/OnlineDistillGCN.

Sheng Zhou, Yucheng Wang, Defang Chen et al.

Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network.Existing KD methods have mainly considered two types of knowledge, namely the individual knowledge and the relational knowledge. However, these two types of knowledge are usually modeled independently while the inherent correlations between them are largely ignored. It is critical for sufficient student network learning to integrate both individual knowledge and relational knowledge while reserving their inherent correlation. In this paper, we propose to distill the novel holistic knowledge based on an attributed graph constructed among instances. The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner. Extensive experiments and ablation studies are conducted on benchmark datasets, the results demonstrate the effectiveness of the proposed method. The code has been published in https://github.com/wyc-ruiker/HKD

Jiefeng Li, Siyuan Bian, Ailing Zeng et al.

Heatmap-based methods dominate in the field of human pose estimation by modelling the output distribution through likelihood heatmaps. In contrast, regression-based methods are more efficient but suffer from inferior performance. In this work, we explore maximum likelihood estimation (MLE) to develop an efficient and effective regression-based methods. From the perspective of MLE, adopting different regression losses is making different assumptions about the output density function. A density function closer to the true distribution leads to a better regression performance. In light of this, we propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution. Concretely, RLE learns the change of the distribution instead of the unreferenced underlying distribution to facilitate the training process. With the proposed reparameterization design, our method is compatible with off-the-shelf flow models. The proposed method is effective, efficient and flexible. We show its potential in various human pose estimation tasks with comprehensive experiments. Compared to the conventional regression paradigm, regression with RLE bring 12.4 mAP improvement on MSCOCO without any test-time overhead. Moreover, for the first time, especially on multi-person pose estimation, our regression method is superior to the heatmap-based methods. Our code is available at https://github.com/Jeff-sjtu/res-loglikelihood-regression

Defang Chen, Jian-Ping Mei, Yuan Zhang et al.

Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model. Recently, feature-map based variants explore knowledge transfer between manually assigned teacher-student pairs in intermediate layers for further improvement. However, layer semantics may vary in different neural networks and semantic mismatch in manual layer associations will lead to performance degeneration due to negative regularization. To address this issue, we propose Semantic Calibration for cross-layer Knowledge Distillation (SemCKD), which automatically assigns proper target layers of the teacher model for each student layer with an attention mechanism. With a learned attention distribution, each student layer distills knowledge contained in multiple teacher layers rather than a specific intermediate layer for appropriate cross-layer supervision. We further provide theoretical analysis of the association weights and conduct extensive experiments to demonstrate the effectiveness of our approach. Code is avaliable at \url{https://github.com/DefangChen/SemCKD}.

Defang Chen, Zhenyu Zhou, Can Wang et al.

Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models. We characterize an implicit denoising trajectory and discuss its vital role in forming the coupled sampling trajectory with a strong shape regularity, regardless of the generated content. We also describe a dynamic programming-based scheme to make the time schedule in sampling better fit the underlying trajectory structure. This simple strategy requires minimal modification to any given ODE-based numerical solvers and incurs negligible computational cost, while delivering superior performance in image generation, especially in $5\sim 10$ function evaluations.

Bo Li, Yingqi Feng, Ming Jin et al.

Ocean salinity plays a vital role in circulation, climate, and marine ecosystems, yet its measurement is often sparse, irregular, and noisy, especially in drifter-based datasets. Traditional approaches, such as remote sensing and optimal interpolation, rely on linearity and stationarity, and are limited by cloud cover, sensor drift, and low satellite revisit rates. While machine learning models offer flexibility, they often fail under severe sparsity and lack principled ways to incorporate physical covariates without specialized sensors. In this paper, we introduce the OceAn Salinity Imputation System (OASIS), a novel diffusion adversarial framework designed to address these challenges.

Defang Chen, Zhenyu Zhou, Can Wang et al.

Diffusion-based generative models employ stochastic differential equations (SDEs) and their equivalent probability flow ordinary differential equations (ODEs) to establish a smooth transformation between complex high-dimensional data distributions and tractable prior distributions. In this paper, we reveal a striking geometric regularity in the deterministic sampling dynamics: each simulated sampling trajectory lies within an extremely low-dimensional subspace, and all trajectories exhibit an almost identical ''boomerang'' shape, regardless of the model architecture, applied conditions, or generated content. We characterize several intriguing properties of these trajectories, particularly under closed-form solutions based on kernel-estimated data modeling. We also demonstrate a practical application of the discovered trajectory regularity by proposing a dynamic programming-based scheme to better align the sampling time schedule with the underlying trajectory structure. This simple strategy requires minimal modification to existing ODE-based numerical solvers, incurs negligible computational overhead, and achieves superior image generation performance, especially in regions with only $5 \sim 10$ function evaluations.

Wanchao Su, Can Wang, Chen Liu et al.

Creating fine-retouched portrait images is tedious and time-consuming even for professional artists. There exist automatic retouching methods, but they either suffer from over-smoothing artifacts or lack generalization ability. To address such issues, we present StyleRetoucher, a novel automatic portrait image retouching framework, leveraging StyleGAN's generation and generalization ability to improve an input portrait image's skin condition while preserving its facial details. Harnessing the priors of pretrained StyleGAN, our method shows superior robustness: a). performing stably with fewer training samples and b). generalizing well on the out-domain data. Moreover, by blending the spatial features of the input image and intermediate features of the StyleGAN layers, our method preserves the input characteristics to the largest extent. We further propose a novel blemish-aware feature selection mechanism to effectively identify and remove the skin blemishes, improving the image skin condition. Qualitative and quantitative evaluations validate the great generalization capability of our method. Further experiments show StyleRetoucher's superior performance to the alternative solutions in the image retouching task. We also conduct a user perceptive study to confirm the superior retouching performance of our method over the existing state-of-the-art alternatives.

Jiaxin Ju, Yizhen Zheng, Huan Yee Koh et al.

Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose $\text{M}^{2}$LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that $\text{M}^{2}$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.

Hailin Zhang, Defang Chen, Can Wang

Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some recent variants attempt to exploit diverse knowledge sources from multiple teachers. However, existing studies mainly integrate knowledge from diverse sources by averaging over multiple teacher predictions or combining them using other various label-free strategies, which may mislead student in the presence of low-quality teacher predictions. To tackle this problem, we propose Confidence-Aware Multi-teacher Knowledge Distillation (CA-MKD), which adaptively assigns sample-wise reliability for each teacher prediction with the help of ground-truth labels, with those teacher predictions close to one-hot labels assigned large weights. Besides, CA-MKD incorporates intermediate layers to stable the knowledge transfer process. Extensive experiments show that our CA-MKD consistently outperforms all compared state-of-the-art methods across various teacher-student architectures.

Jiawei Chen, Chengquan Jiang, Can Wang et al.

Sampling strategies have been widely applied in many recommendation systems to accelerate model learning from implicit feedback data. A typical strategy is to draw negative instances with uniform distribution, which however will severely affect model's convergency, stability, and even recommendation accuracy. A promising solution for this problem is to over-sample the ``difficult'' (a.k.a informative) instances that contribute more on training. But this will increase the risk of biasing the model and leading to non-optimal results. Moreover, existing samplers are either heuristic, which require domain knowledge and often fail to capture real ``difficult'' instances; or rely on a sampler model that suffers from low efficiency. To deal with these problems, we propose an efficient and effective collaborative sampling method CoSam, which consists of: (1) a collaborative sampler model that explicitly leverages user-item interaction information in sampling probability and exhibits good properties of normalization, adaption, interaction information awareness, and sampling efficiency; and (2) an integrated sampler-recommender framework, leveraging the sampler model in prediction to offset the bias caused by uneven sampling. Correspondingly, we derive a fast reinforced training algorithm of our framework to boost the sampler performance and sampler-recommender collaboration. Extensive experiments on four real-world datasets demonstrate the superiority of the proposed collaborative sampler model and integrated sampler-recommender framework.

Ye Tao, Can Wang, Lina Yao et al.

Recommendation system plays an important role in online web applications. Sequential recommender further models user short-term preference through exploiting information from latest user-item interaction history. Most of the sequential recommendation methods neglect the importance of ever-changing item popularity. We propose the model from the intuition that items with most user interactions may be popular in the past but could go out of fashion in recent days. To this end, this paper proposes a novel sequential recommendation approach dubbed TRec, TRec learns item trend information from implicit user interaction history and incorporates item trend information into next item recommendation tasks. Then a self-attention mechanism is used to learn better node representation. Our model is trained via pairwise rank-based optimization. We conduct extensive experiments with seven baseline methods on four benchmark datasets, The empirical result shows our approach outperforms other stateof-the-art methods while maintains a superiorly low runtime cost. Our study demonstrates the importance of item trend information in recommendation system designs, and our method also possesses great efficiency which enables it to be practical in real-world scenarios.

Zhe Liu, Lina Yao, Lei Bai et al.

It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class. In this work, we propose a novel end-to-end knowledge directed adversarial learning framework, which portrays the class-conditioned intraclass disparity using two competitive encoding distributions and learns the purified latent codes by denoising learned disparity. Furthermore, the domain knowledge is incorporated in an unsupervised manner to guide the optimization and further boosts the performance. The experiments on four HAR benchmark datasets demonstrate the robustness and generalization of our proposed methods over a set of state-of-the-art. We further prove the effectiveness of automatic domain knowledge incorporation in performance enhancement.

Guang Liang, Shangfei Wang, Can Wang

Current facial expression recognition methods fail to simultaneously cope with pose and subject variations. In this paper, we propose a novel unsupervised adversarial domain adaptation method which can alleviate both variations at the same time. Specially, our method consists of three learning strategies: adversarial domain adaptation learning, cross adversarial feature learning, and reconstruction learning. The first aims to learn pose- and expression-related feature representations in the source domain and adapt both feature distributions to that of the target domain by imposing adversarial learning. By using personalized adversarial domain adaptation, this learning strategy can alleviate subject variations and exploit information from the source domain to help learning in the target domain. The second serves to perform feature disentanglement between pose- and expression-related feature representations by impulsing pose-related feature representations expression-undistinguished and the expression-related feature representations pose-undistinguished. The last can further boost feature learning by applying face image reconstructions so that the learned expression-related feature representations are more pose- and identity-robust. Experimental results on four benchmark datasets demonstrate the effectiveness of the proposed method.

Lei Bai, Lina Yao, Can Li et al.

Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an evolving traffic system. Recent works focus on designing complicated graph neural network architectures to capture shared patterns with the help of pre-defined graphs. In this paper, we argue that learning node-specific patterns is essential for traffic forecasting while the pre-defined graph is avoidable. To this end, we propose two adaptive modules for enhancing Graph Convolutional Network (GCN) with new capabilities: 1) a Node Adaptive Parameter Learning (NAPL) module to capture node-specific patterns; 2) a Data Adaptive Graph Generation (DAGG) module to infer the inter-dependencies among different traffic series automatically. We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks. Our experiments on two real-world traffic datasets show AGCRN outperforms state-of-the-art by a significant margin without pre-defined graphs about spatial connections.

Jiawei Chen, Can Wang, Sheng Zhou et al.

Recommendation from implicit feedback is a highly challenging task due to the lack of the reliable observed negative data. A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence. Naturally, how to assign confidence weights and how to handle the large number of the unobserved data are two key problems for implicit recommendation models. However, existing methods either pursuit fast learning by manually assigning simple confidence weights, which lacks flexibility and may create empirical bias in evaluating user's preference; or adaptively infer personalized confidence weights but suffer from low efficiency. To achieve both adaptive weights assignment and efficient model learning, we propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder. The personalized data confidence weights are adaptively assigned with a parameterized neural network (function) and the network can be inferred from the data. Further, to support fast and stable learning of FAWMF, a new specific batch-based learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number of observed data. Extensive experiments on real-world datasets demonstrate the superiority of the proposed FAWMF and its learning algorithm fBGD.

Defang Chen, Jian-Ping Mei, Can Wang et al.

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always available. Recently proposed online variants use the aggregated intermediate predictions of multiple student models as targets to train each student model. Although group-derived targets give a good recipe for teacher-free distillation, group members are homogenized quickly with simple aggregation functions, leading to early saturated solutions. In this work, we propose Online Knowledge Distillation with Diverse peers (OKDDip), which performs two-level distillation during training with multiple auxiliary peers and one group leader. In the first-level distillation, each auxiliary peer holds an individual set of aggregation weights generated with an attention-based mechanism to derive its own targets from predictions of other auxiliary peers. Learning from distinct target distributions helps to boost peer diversity for effectiveness of group-based distillation. The second-level distillation is performed to transfer the knowledge in the ensemble of auxiliary peers further to the group leader, i.e., the model used for inference. Experimental results show that the proposed framework consistently gives better performance than state-of-the-art approaches without sacrificing training or inference complexity, demonstrating the effectiveness of the proposed two-level distillation framework.

Zhen Zhang, Jiajun Bu, Martin Ester et al.

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we propose a novel graph pooling operator, called Hierarchical Graph Pooling with Structure Learning (HGP-SL), which can be integrated into various graph neural network architectures. HGP-SL incorporates graph pooling and structure learning into a unified module to generate hierarchical representations of graphs. More specifically, the graph pooling operation adaptively selects a subset of nodes to form an induced subgraph for the subsequent layers. To preserve the integrity of graph's topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. By combining HGP-SL operator with graph neural networks, we perform graph level representation learning with focus on graph classification task. Experimental results on six widely used benchmarks demonstrate the effectiveness of our proposed model.

Sheng Zhou, Jiajun Bu, Xin Wang et al.

Heterogeneous information network (HIN) embedding has recently attracted much attention due to its effectiveness in dealing with the complex heterogeneous data. Meta path, which connects different object types with various semantic meanings, is widely used by existing HIN embedding works. However, several challenges have not been addressed so far. First, different meta paths convey different semantic meanings, while existing works assume that all nodes share same weights for meta paths and ignore the personalized preferences of different nodes on different meta paths. Second, given a meta path, nodes in HIN are connected by path instances while existing works fail to fully explore the differences between path instances that reflect nodes' preferences in the semantic space. rTo tackle the above challenges, we propose aHierarchical Attentive Heterogeneous information network Embedding (HAHE) model to capture the personalized preferences on meta paths and path instances in each semantic space. As path instances are based on a particular meta path, a hierarchical attention mechanism is naturally utilized to model the personalized preference on meta paths and path instances. Extensive experiments on several real-world datasets show that our proposed \model model significantly outperforms the state-of-the-art methods in terms of various data mining tasks.

Xiang Zhang, Lina Yao, Chaoran Huang et al.

Multimodal wearable sensor data classification plays an important role in ubiquitous computing and has a wide range of applications in scenarios from healthcare to entertainment. However, most existing work in this field employs domain-specific approaches and is thus ineffective in complex sit- uations where multi-modality sensor data are col- lected. Moreover, the wearable sensor data are less informative than the conventional data such as texts or images. In this paper, to improve the adapt- ability of such classification methods across differ- ent application domains, we turn this classification task into a game and apply a deep reinforcement learning scheme to deal with complex situations dynamically. Additionally, we introduce a selective attention mechanism into the reinforcement learn- ing scheme to focus on the crucial dimensions of the data. This mechanism helps to capture extra information from the signal and thus it is able to significantly improve the discriminative power of the classifier. We carry out several experiments on three wearable sensor datasets and demonstrate the competitive performance of the proposed approach compared to several state-of-the-art baselines.

Kui Zhao, Can Wang

Sales forecast is an essential task in E-commerce and has a crucial impact on making informed business decisions. It can help us to manage the workforce, cash flow and resources such as optimizing the supply chain of manufacturers etc. Sales forecast is a challenging problem in that sales is affected by many factors including promotion activities, price changes, and user preferences etc. Traditional sales forecast techniques mainly rely on historical sales data to predict future sales and their accuracies are limited. Some more recent learning-based methods capture more information in the model to improve the forecast accuracy. However, these methods require case-by-case manual feature engineering for specific commercial scenarios, which is usually a difficult, time-consuming task and requires expert knowledge. To overcome the limitations of existing methods, we propose a novel approach in this paper to learn effective features automatically from the structured data using the Convolutional Neural Network (CNN). When fed with raw log data, our approach can automatically extract effective features from that and then forecast sales using those extracted features. We test our method on a large real-world dataset from CaiNiao.com and the experimental results validate the effectiveness of our method.

Yonghong Yu, Can Wang, Yang Gao

Recommender system has attracted lots of attentions since it helps users alleviate the information overload problem. Matrix factorization technique is one of the most widely employed collaborative filtering techniques in the research of recommender systems due to its effectiveness and efficiency in dealing with very large user-item rating matrices. Recently, based on the intuition that additional information provides useful insights for matrix factorization techniques, several recommendation algorithms have utilized additional information to improve the performance of matrix factorization methods. However, the majority focus on dealing with the cold start user problem and ignore the cold start item problem. In addition, there are few suitable similarity measures for these content enhanced matrix factorization approaches to compute the similarity between categorical items. In this paper, we propose attributes coupling based item enhanced matrix factorization method by incorporating item attribute information into matrix factorization technique as well as adapting the coupled object similarity to capture the relationship between items. Item attribute information is formed as an item relationship regularization term to regularize the process of matrix factorization. Specifically, the similarity between items is measured by the Coupled Object Similarity considering coupling between items. Experimental results on two real data sets show that our proposed method outperforms state-of-the-art recommendation algorithms and can effectively cope with the cold start item problem when more item attribute information is available.

Kaixu Zhang, Can Wang, Maosong Sun

Chinese word segmentation is a fundamental task for Chinese language processing. The granularity mismatch problem is the main cause of the errors. This paper showed that the binary tree representation can store outputs with different granularity. A binary tree based framework is also designed to overcome the granularity mismatch problem. There are two steps in this framework, namely tree building and tree pruning. The tree pruning step is specially designed to focus on the granularity problem. Previous work for Chinese word segmentation such as the sequence tagging can be easily employed in this framework. This framework can also provide quantitative error analysis methods. The experiments showed that after using a more sophisticated tree pruning function for a state-of-the-art conditional random field based baseline, the error reduction can be up to 20%.