Jie Xu

Jie Xu, Viktor Makoviychuk, Yashraj Narang et al. · gatech, nvidia

Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators. However, inherent problems such as local minima and exploding/vanishing numerical gradients prevent these methods from being generally applied to control tasks with complex contact-rich dynamics, such as humanoid locomotion in classical RL benchmarks. In this work we present a high-performance differentiable simulator and a new policy learning algorithm (SHAC) that can effectively leverage simulation gradients, even in the presence of non-smoothness. Our learning algorithm alleviates problems with local minima through a smooth critic function, avoids vanishing/exploding gradients through a truncated learning window, and allows many physical environments to be run in parallel. We evaluate our method on classical RL control tasks, and show substantial improvements in sample efficiency and wall-clock time over state-of-the-art RL and differentiable simulation-based algorithms. In addition, we demonstrate the scalability of our method by applying it to the challenging high-dimensional problem of muscle-actuated locomotion with a large action space, achieving a greater than 17x reduction in training time over the best-performing established RL algorithm.

Xinghang Li, Minghuan Liu, Hanbo Zhang et al.

Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of existing vision-language models (VLMs) with simple fine-tuning on robotics data. To this end, we derive a simple and novel vision-language manipulation framework, dubbed RoboFlamingo, built upon the open-source VLMs, OpenFlamingo. Unlike prior works, RoboFlamingo utilizes pre-trained VLMs for single-step vision-language comprehension, models sequential history information with an explicit policy head, and is slightly fine-tuned by imitation learning only on language-conditioned manipulation datasets. Such a decomposition provides RoboFlamingo the flexibility for open-loop control and deployment on low-performance platforms. By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control. Our extensive experimental results also reveal several interesting conclusions regarding the behavior of different pre-trained VLMs on manipulation tasks. We believe RoboFlamingo has the potential to be a cost-effective and easy-to-use solution for robotics manipulation, empowering everyone with the ability to fine-tune their own robotics policy.

Yazhou Ren, Jingyu Pu, Zhimeng Yang et al.

Cluster analysis plays an indispensable role in machine learning and data mining. Learning a good data representation is crucial for clustering algorithms. Recently, deep clustering, which can learn clustering-friendly representations using deep neural networks, has been broadly applied in a wide range of clustering tasks. Existing surveys for deep clustering mainly focus on the single-view fields and the network architectures, ignoring the complex application scenarios of clustering. To address this issue, in this paper we provide a comprehensive survey for deep clustering in views of data sources. With different data sources and initial conditions, we systematically distinguish the clustering methods in terms of methodology, prior knowledge, and architecture. Concretely, deep clustering methods are introduced according to four categories, i.e., traditional single-view deep clustering, semi-supervised deep clustering, deep multi-view clustering, and deep transfer clustering. Finally, we discuss the open challenges and potential future opportunities in different fields of deep clustering.

Liang Peng, Nan Wang, Jie Xu et al.

In this work, we focus on the challenging task, neuro-disease classification, using functional magnetic resonance imaging (fMRI). In population graph-based disease analysis, graph convolutional neural networks (GCNs) have achieved remarkable success. However, these achievements are inseparable from abundant labeled data and sensitive to spurious signals. To improve fMRI representation learning and classification under a label-efficient setting, we propose a novel and theory-driven self-supervised learning (SSL) framework on GCNs, namely Graph CCA for Temporal self-supervised learning on fMRI analysis GATE. Concretely, it is demanding to design a suitable and effective SSL strategy to extract formation and robust features for fMRI. To this end, we investigate several new graph augmentation strategies from fMRI dynamic functional connectives (FC) for SSL training. Further, we leverage canonical-correlation analysis (CCA) on different temporal embeddings and present the theoretical implications. Consequently, this yields a novel two-step GCN learning procedure comprised of (i) SSL on an unlabeled fMRI population graph and (ii) fine-tuning on a small labeled fMRI dataset for a classification task. Our method is tested on two independent fMRI datasets, demonstrating superior performance on autism and dementia diagnosis.

Chengsheng Mao, Jie Xu, Luke Rasmussen et al.

Objective: We develop a deep learning framework based on the pre-trained Bidirectional Encoder Representations from Transformers (BERT) model using unstructured clinical notes from electronic health records (EHRs) to predict the risk of disease progression from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD). Materials and Methods: We identified 3657 patients diagnosed with MCI together with their progress notes from Northwestern Medicine Enterprise Data Warehouse (NMEDW) between 2000-2020. The progress notes no later than the first MCI diagnosis were used for the prediction. We first preprocessed the notes by deidentification, cleaning and splitting, and then pretrained a BERT model for AD (AD-BERT) based on the publicly available Bio+Clinical BERT on the preprocessed notes. The embeddings of all the sections of a patient's notes processed by AD-BERT were combined by MaxPooling to compute the probability of MCI-to-AD progression. For replication, we conducted a similar set of experiments on 2563 MCI patients identified at Weill Cornell Medicine (WCM) during the same timeframe. Results: Compared with the 7 baseline models, the AD-BERT model achieved the best performance on both datasets, with Area Under receiver operating characteristic Curve (AUC) of 0.8170 and F1 score of 0.4178 on NMEDW dataset and AUC of 0.8830 and F1 score of 0.6836 on WCM dataset. Conclusion: We developed a deep learning framework using BERT models which provide an effective solution for prediction of MCI-to-AD progression using clinical note analysis.

Xiaoming Shi, Jie Xu, Jinru Ding et al.

There is an increasing interest in developing LLMs for medical diagnosis to improve diagnosis efficiency. Despite their alluring technological potential, there is no unified and comprehensive evaluation criterion, leading to the inability to evaluate the quality and potential risks of medical LLMs, further hindering the application of LLMs in medical treatment scenarios. Besides, current evaluations heavily rely on labor-intensive interactions with LLMs to obtain diagnostic dialogues and human evaluation on the quality of diagnosis dialogue. To tackle the lack of unified and comprehensive evaluation criterion, we first initially establish an evaluation criterion, termed LLM-specific Mini-CEX to assess the diagnostic capabilities of LLMs effectively, based on original Mini-CEX. To address the labor-intensive interaction problem, we develop a patient simulator to engage in automatic conversations with LLMs, and utilize ChatGPT for evaluating diagnosis dialogues automatically. Experimental results show that the LLM-specific Mini-CEX is adequate and necessary to evaluate medical diagnosis dialogue. Besides, ChatGPT can replace manual evaluation on the metrics of humanistic qualities and provides reproducible and automated comparisons between different LLMs.

Jie Xu, Yazhou Ren, Xiaolong Wang et al.

Multi-view clustering (MVC) aims at exploring category structures among multi-view data in self-supervised manners. Multiple views provide more information than single views and thus existing MVC methods can achieve satisfactory performance. However, their performance might seriously degenerate when the views are noisy in practical multi-view scenarios. In this paper, we formally investigate the drawback of noisy views and then propose a theoretically grounded deep MVC method (namely MVCAN) to address this issue. Specifically, we propose a novel MVC objective that enables un-shared parameters and inconsistent clustering predictions across multiple views to reduce the side effects of noisy views. Furthermore, a two-level multi-view iterative optimization is designed to generate robust learning targets for refining individual views' representation learning. Theoretical analysis reveals that MVCAN works by achieving the multi-view consistency, complementarity, and noise robustness. Finally, experiments on extensive public datasets demonstrate that MVCAN outperforms state-of-the-art methods and is robust against the existence of noisy views.

Yingze Xie, Jie Xu, LiQiang Qiao et al.

Sentiment transfer aims at revising the input text to satisfy a given sentiment polarity while retaining the original semantic content. The nucleus of sentiment transfer lies in precisely separating the sentiment information from the content information. Existing explicit approaches generally identify and mask sentiment tokens simply based on prior linguistic knowledge and manually-defined rules, leading to low generality and undesirable transfer performance. In this paper, we view the positions to be masked as the learnable parameters, and further propose a novel AM-ST model to learn adaptive task-relevant masks based on the attention mechanism. Moreover, a sentiment-aware masked language model is further proposed to fill in the blanks in the masked positions by incorporating both context and sentiment polarity to capture the multi-grained semantics comprehensively. AM-ST is thoroughly evaluated on two popular datasets, and the experimental results demonstrate the superiority of our proposal.

Jieming Bian, Lei Wang, Kun Yang et al.

Over the past few years, Federated Learning (FL) has become a popular distributed machine learning paradigm. FL involves a group of clients with decentralized data who collaborate to learn a common model under the coordination of a centralized server, with the goal of protecting clients' privacy by ensuring that local datasets never leave the clients and that the server only performs model aggregation. However, in realistic scenarios, the server may be able to collect a small amount of data that approximately mimics the population distribution and has stronger computational ability to perform the learning process. To address this, we focus on the hybrid FL framework in this paper. While previous hybrid FL work has shown that the alternative training of clients and server can increase convergence speed, it has focused on the scenario where clients fully participate and ignores the negative effect of partial participation. In this paper, we provide theoretical analysis of hybrid FL under clients' partial participation to validate that partial participation is the key constraint on convergence speed. We then propose a new algorithm called FedCLG, which investigates the two-fold role of the server in hybrid FL. Firstly, the server needs to process the training steps using its small amount of local datasets. Secondly, the server's calculated gradient needs to guide the participated clients' training and the server's aggregation. We validate our theoretical findings through numerical experiments, which show that our proposed method FedCLG outperforms state-of-the-art methods.

Jieming Bian, Jie Xu

This paper presents a study on asynchronous Federated Learning (FL) in a mobile network setting. The majority of FL algorithms assume that communication between clients and the server is always available, however, this is not the case in many real-world systems. To address this issue, the paper explores the impact of mobility on the convergence performance of asynchronous FL. By exploiting mobility, the study shows that clients can indirectly communicate with the server through another client serving as a relay, creating additional communication opportunities. This enables clients to upload local model updates sooner or receive fresher global models. We propose a new FL algorithm, called FedMobile, that incorporates opportunistic relaying and addresses key questions such as when and how to relay. We prove that FedMobile achieves a convergence rate $O(\frac{1}{\sqrt{NT}})$, where $N$ is the number of clients and $T$ is the number of communication slots, and show that the optimal design involves an interesting trade-off on the best timing of relaying. The paper also presents an extension that considers data manipulation before relaying to reduce the cost and enhance privacy. Experiment results on a synthetic dataset and two real-world datasets verify our theoretical findings.

Heqiang Wang, Jieming Bian, Jie Xu

In this study, we address the emerging field of Streaming Federated Learning (SFL) and propose local cache update rules to manage dynamic data distributions and limited cache capacity. Traditional federated learning relies on fixed data sets, whereas in SFL, data is streamed, and its distribution changes over time, leading to discrepancies between the local training dataset and long-term distribution. To mitigate this problem, we propose three local cache update rules - First-In-First-Out (FIFO), Static Ratio Selective Replacement (SRSR), and Dynamic Ratio Selective Replacement (DRSR) - that update the local cache of each client while considering the limited cache capacity. Furthermore, we derive a convergence bound for our proposed SFL algorithm as a function of the distribution discrepancy between the long-term data distribution and the client's local training dataset. We then evaluate our proposed algorithm on two datasets: a network traffic classification dataset and an image classification dataset. Our experimental results demonstrate that our proposed local cache update rules significantly reduce the distribution discrepancy and outperform the baseline methods. Our study advances the field of SFL and provides practical cache management solutions in federated learning.

Jieming Bian, Cong Shen, Jie Xu

Federated Learning (FL) is a communication-efficient and privacy-preserving distributed machine learning framework that has gained a significant amount of research attention recently. Despite the different forms of FL algorithms (e.g., synchronous FL, asynchronous FL) and the underlying optimization methods, nearly all existing works implicitly assumed the existence of a communication infrastructure that facilitates the direct communication between the server and the clients for the model data exchange. This assumption, however, does not hold in many real-world applications that can benefit from distributed learning but lack a proper communication infrastructure (e.g., smart sensing in remote areas). In this paper, we propose a novel FL framework, named FedEx (short for FL via Model Express Delivery), that utilizes mobile transporters (e.g., Unmanned Aerial Vehicles) to establish indirect communication channels between the server and the clients. Two algorithms, called FedEx-Sync and FedEx-Async, are developed depending on whether the transporters adopt a synchronized or an asynchronized schedule. Even though the indirect communications introduce heterogeneous delays to clients for both the global model dissemination and the local model collection, we prove the convergence of both versions of FedEx. The convergence analysis subsequently sheds lights on how to assign clients to different transporters and design the routes among the clients. The performance of FedEx is evaluated through experiments in a simulated network on two public datasets.

Jieming Bian, Cong Shen, Jie Xu

Federated Learning (FL) is a machine learning approach that enables the creation of shared models for powerful applications while allowing data to remain on devices. This approach provides benefits such as improved data privacy, security, and reduced latency. However, in some systems, direct communication between clients and servers may not be possible, such as remote areas without proper communication infrastructure. To overcome this challenge, a new framework called FedEx (Federated Learning via Model Express Delivery) is proposed. This framework employs mobile transporters, such as UAVs, to establish indirect communication channels between the server and clients. These transporters act as intermediaries and allow for model information exchange. The use of indirect communication presents new challenges for convergence analysis and optimization, as the delay introduced by the transporters' movement creates issues for both global model dissemination and local model collection. To address this, two algorithms, FedEx-Sync and FedEx-Async, are proposed for synchronized and asynchronized learning at the transporter level. Additionally, a bi-level optimization algorithm is proposed to solve the joint client assignment and route planning problem. Experimental validation using two public datasets in a simulated network demonstrates consistent results with the theory, proving the efficacy of FedEx.

Heqiang Wang, Jie Xu

Federated learning (FL) is a new distributed machine learning framework known for its benefits on data privacy and communication efficiency. Since full client participation in many cases is infeasible due to constrained resources, partial participation FL algorithms have been investigated that proactively select/sample a subset of clients, aiming to achieve learning performance close to the full participation case. This paper studies a passive partial client participation scenario that is much less well understood, where partial participation is a result of external events, namely client dropout, rather than a decision of the FL algorithm. We cast FL with client dropout as a special case of a larger class of FL problems where clients can submit substitute (possibly inaccurate) local model updates. Based on our convergence analysis, we develop a new algorithm FL-FDMS that discovers friends of clients (i.e., clients whose data distributions are similar) on-the-fly and uses friends' local updates as substitutes for the dropout clients, thereby reducing the substitution error and improving the convergence performance. A complexity reduction mechanism is also incorporated into FL-FDMS, making it both theoretically sound and practically useful. Experiments on MNIST and CIFAR-10 confirmed the superior performance of FL-FDMS in handling client dropout in FL.

Letian Zhang, Jie Xu

Multi-human 3D pose estimation plays a key role in establishing a seamless connection between the real world and the virtual world. Recent efforts adopted a two-stage framework that first builds 2D pose estimations in multiple camera views from different perspectives and then synthesizes them into 3D poses. However, the focus has largely been on developing new computer vision algorithms on the offline video datasets without much consideration on the energy constraints in real-world systems with flexibly-deployed and battery-powered cameras. In this paper, we propose an energy-efficient edge-assisted multiple-camera system, dubbed E$^3$Pose, for real-time multi-human 3D pose estimation, based on the key idea of adaptive camera selection. Instead of always employing all available cameras to perform 2D pose estimations as in the existing works, E$^3$Pose selects only a subset of cameras depending on their camera view qualities in terms of occlusion and energy states in an adaptive manner, thereby reducing the energy consumption (which translates to extended battery lifetime) and improving the estimation accuracy. To achieve this goal, E$^3$Pose incorporates an attention-based LSTM to predict the occlusion information of each camera view and guide camera selection before cameras are selected to process the images of a scene, and runs a camera selection algorithm based on the Lyapunov optimization framework to make long-term adaptive selection decisions. We build a prototype of E$^3$Pose on a 5-camera testbed, demonstrate its feasibility and evaluate its performance. Our results show that a significant energy saving (up to 31.21%) can be achieved while maintaining a high 3D pose estimation accuracy comparable to state-of-the-art methods.

Jie Xu, Yazhou Ren, Huayi Tang et al.

Multi-view clustering is an important research topic due to its capability to utilize complementary information from multiple views. However, there are few methods to consider the negative impact caused by certain views with unclear clustering structures, resulting in poor multi-view clustering performance. To address this drawback, we propose self-supervised discriminative feature learning for deep multi-view clustering (SDMVC). Concretely, deep autoencoders are applied to learn embedded features for each view independently. To leverage the multi-view complementary information, we concatenate all views' embedded features to form the global features, which can overcome the negative impact of some views' unclear clustering structures. In a self-supervised manner, pseudo-labels are obtained to build a unified target distribution to perform multi-view discriminative feature learning. During this process, global discriminative information can be mined to supervise all views to learn more discriminative features, which in turn are used to update the target distribution. Besides, this unified target distribution can make SDMVC learn consistent cluster assignments, which accomplishes the clustering consistency of multiple views while preserving their features' diversity. Experiments on various types of multi-view datasets show that SDMVC outperforms 14 competitors including classic and state-of-the-art methods. The code is available at https://github.com/SubmissionsIn/SDMVC.

Zhonghao Lyu, Yuchen Li, Guangxu Zhu et al.

In some applications, edge learning is experiencing a shift in focusing from conventional learning from scratch to new two-stage learning unifying pre-training and task-specific fine-tuning. This paper considers the problem of joint communication and computation resource management in a two-stage edge learning system. In this system, model pre-training is first conducted at an edge server via centralized learning on local pre-stored general data, and then task-specific fine-tuning is performed at edge devices based on the pre-trained model via federated edge learning. For the two-stage learning model, we first analyze the convergence behavior (in terms of the average squared gradient norm bound), which characterizes the impacts of various system parameters such as the number of learning rounds and batch sizes in the two stages on the convergence rate. Based on our analytical results, we then propose a joint communication and computation resource management design to minimize an average squared gradient norm bound, subject to constraints on the transmit power, overall system energy consumption, and training delay. The decision variables include the number of learning rounds, batch sizes, clock frequencies, and transmit power control for both pre-training and fine-tuning stages. Finally, numerical results are provided to evaluate the effectiveness of our proposed design. It is shown that the proposed joint resource management over the pre-training and fine-tuning stages well balances the system performance trade-off among the training accuracy, delay, and energy consumption. The proposed design is also shown to effectively leverage the inherent trade-off between pre-training and fine-tuning, which arises from the differences in data distribution between pre-stored general data versus real-time task-specific data, thus efficiently optimizing overall system performance.

Lei Lu, Zhepeng Wang, Runxue Bao et al.

Existing pruning techniques for large language models (LLMs) targeting domain-specific applications typically follow a two-stage process: pruning the pretrained general-purpose LLMs and then fine-tuning the pruned LLMs on specific domains. However, the pruning decisions, derived from the pretrained weights, remain unchanged during fine-tuning, even if the weights have been updated. Therefore, such a combination of the pruning decisions and the finetuned weights may be suboptimal, leading to non-negligible performance degradation. To address these limitations, we propose ATP: All-in-One Tuning and Structural Pruning, a unified one-stage structural pruning and fine-tuning approach that dynamically identifies the current optimal substructure throughout the fine-tuning phase via a trainable pruning decision generator. Moreover, given the limited available data for domain-specific applications, Low-Rank Adaptation (LoRA) becomes a common technique to fine-tune the LLMs. In ATP, we introduce LoRA-aware forward and sparsity regularization to ensure that the substructures corresponding to the learned pruning decisions can be directly removed after the ATP process. ATP outperforms the state-of-the-art two-stage pruning methods on tasks in the legal and healthcare domains. More specifically, ATP recovers up to 88% and 91% performance of the dense model when pruning 40% parameters of LLaMA2-7B and LLaMA3-8B models, respectively.

Zhen Yang, Hongyi Lin, Yifan He et al.

In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns regarding data contamination and its potential impact on model performance evaluation. This paper presents a systematic empirical study to investigate the fine-grained data contamination on code intelligence tasks. Our study involves diverse representative PLMs, namely RoBERTa and GPT-2, and LLMs, namely LLaMA and StarCoder, covering three major tasks: code translation, code generation, and code summarization. We categorize contamination scenarios into four types according to the code intelligence practice, namely input-only, output-only, unpaired, and paired contamination settings, and construct corresponding experimental and control groups for exploration. Experimental results show that, under the pre-training, fine-tuning, and inference paradigm adopted by PLMs, even deliberately injecting paired contamination does not lead to significant performance overestimation. But direct inference or small-scale fine-tuning uncovers the contamination effects. In contrast, LLMs with pre-training and inference paradigm are significantly affected by the paired contamination. Apart from the above, other contamination scenarios have no impact on both PLMs and LLMs. Our findings challenge the conventional belief that contamination inevitably leads to performance overestimation, providing new insights into the evaluation and deployment of code intelligence models.

Jingzhi Gong, Rafail Giavrimis, Paul Brookes et al.

There is a growing interest in leveraging multiple large language models (LLMs) for automated code optimization. However, industrial platforms deploying multiple LLMs face a critical challenge: prompts optimized for one LLM often fail with others, requiring expensive model-specific prompt engineering. This cross-model prompt engineering bottleneck severely limits the practical deployment of multi-LLM systems in production environments. We introduce Meta-Prompted Code Optimization (MPCO), a framework that automatically generates high-quality, task-specific prompts across diverse LLMs while maintaining industrial efficiency requirements. MPCO leverages metaprompting to dynamically synthesize context-aware optimization prompts by integrating project metadata, task requirements, and LLM-specific contexts. It is an essential part of the ARTEMIS code optimization platform for automated validation and scaling. Our comprehensive evaluation on five real-world codebases with 366 hours of runtime benchmarking demonstrates MPCO's effectiveness: it achieves overall performance improvements up to 19.06% with the best statistical rank across all systems compared to baseline methods. Analysis shows that 96% of the top-performing optimizations stem from meaningful edits. Through systematic ablation studies and meta-prompter sensitivity analysis, we identify that comprehensive context integration is essential for effective meta-prompting and that major LLMs can serve effectively as meta-prompters, providing actionable insights for industrial practitioners.

Jinru Ding, Lu Lu, Chao Ding et al.

Recent advances in medical large language models (LLMs), multimodal models, and agents demand evaluation frameworks that reflect real clinical workflows and safety constraints. We present MedBench v4, a nationwide, cloud-based benchmarking infrastructure comprising over 700,000 expert-curated tasks spanning 24 primary and 91 secondary specialties, with dedicated tracks for LLMs, multimodal models, and agents. Items undergo multi-stage refinement and multi-round review by clinicians from more than 500 institutions, and open-ended responses are scored by an LLM-as-a-judge calibrated to human ratings. We evaluate 15 frontier models. Base LLMs reach a mean overall score of 54.1/100 (best: Claude Sonnet 4.5, 62.5/100), but safety and ethics remain low (18.4/100). Multimodal models perform worse overall (mean 47.5/100; best: GPT-5, 54.9/100), with solid perception yet weaker cross-modal reasoning. Agents built on the same backbones substantially improve end-to-end performance (mean 79.8/100), with Claude Sonnet 4.5-based agents achieving up to 85.3/100 overall and 88.9/100 on safety tasks. MedBench v4 thus reveals persisting gaps in multimodal reasoning and safety for base models, while showing that governance-aware agentic orchestration can markedly enhance benchmarked clinical readiness without sacrificing capability. By aligning tasks with Chinese clinical guidelines and regulatory priorities, the platform offers a practical reference for hospitals, developers, and policymakers auditing medical AI.

Megan Tjandrasuwita, Jie Xu, Armando Solar-Lezama et al.

Robots are often built from standardized assemblies, (e.g. arms, legs, or fingers), but each robot must be trained from scratch to control all the actuators of all the parts together. In this paper we demonstrate a new approach that takes a single robot and its controller as input and produces a set of modular controllers for each of these assemblies such that when a new robot is built from the same parts, its control can be quickly learned by reusing the modular controllers. We achieve this with a framework called MeMo which learns (Me)aningful, (Mo)dular controllers. Specifically, we propose a novel modularity objective to learn an appropriate division of labor among the modules. We demonstrate that this objective can be optimized simultaneously with standard behavior cloning loss via noise injection. We benchmark our framework in locomotion and grasping environments on simple to complex robot morphology transfer. We also show that the modules help in task transfer. On both structure and task transfer, MeMo achieves improved training efficiency to graph neural network and Transformer baselines.

Shicheng Gao, Jie Xu, Xiaosen Li et al.

K-core decomposition is a commonly used metric to analyze graph structure or study the relative importance of nodes in complex graphs. Recent years have seen rapid growth in the scale of the graph, especially in industrial settings. For example, our industrial partner runs popular social applications with billions of users and is able to gather a rich set of user data. As a result, applying K-core decomposition on large graphs has attracted more and more attention from academics and the industry. A simple but effective method to deal with large graphs is to train them in the distributed settings, and some distributed K-core decomposition algorithms are also proposed. Despite their effectiveness, we experimentally and theoretically observe that these algorithms consume too many resources and become unstable on super-large-scale graphs, especially when the given resources are limited. In this paper, we deal with those super-large-scale graphs and propose a divide-and-conquer strategy on top of the distributed K-core decomposition algorithm. We evaluate our approach on three large graphs. The experimental results show that the consumption of resources can be significantly reduced, and the calculation on large-scale graphs becomes more stable than the existing methods. For example, the distributed K-core decomposition algorithm can scale to a large graph with 136 billion edges without losing correctness with our divide-and-conquer technique.

Yang Bai, Lixing Chen, Shaolei Ren et al.

The rapid uptake of intelligent applications is pushing deep learning (DL) capabilities to Internet-of-Things (IoT). Despite the emergence of new tools for embedding deep neural networks (DNNs) into IoT devices, providing satisfactory Quality of Experience (QoE) to users is still challenging due to the heterogeneity in DNN architectures, IoT devices, and user preferences. This paper studies automated customization for DL inference on IoT devices (termed as on-thing inference), and our goal is to enhance user QoE by configuring the on-thing inference with an appropriate DNN for users under different usage scenarios. The core of our method is a DNN selection module that learns user QoE patterns on-the-fly and identifies the best-fit DNN for on-thing inference with the learned knowledge. It leverages a novel online learning algorithm, NeuralUCB, that has excellent generalization ability for handling various user QoE patterns. We also embed the knowledge transfer technique in NeuralUCB to expedite the learning process. However, NeuralUCB frequently solicits QoE ratings from users, which incurs non-negligible inconvenience. To address this problem, we design feedback solicitation schemes to reduce the number of QoE solicitations while maintaining the learning efficiency of NeuralUCB. A pragmatic problem, aggregated QoE, is further investigated to improve the practicality of our framework. We conduct experiments on both synthetic and real-world data. The results indicate that our method efficiently learns the user QoE pattern with few solicitations and provides drastic QoE enhancement for IoT devices.

Zhe Qu, Rui Duan, Lixing Chen et al.

Federated Learning (FL) has been considered as an appealing framework to tackle data privacy issues of mobile devices compared to conventional Machine Learning (ML). Using Edge Servers (ESs) as intermediaries to perform model aggregation in proximity can reduce the transmission overhead, and it enables great potentials in low-latency FL, where the hierarchical architecture of FL (HFL) has been attracted more attention. Designing a proper client selection policy can significantly improve training performance, and it has been extensively used in FL studies. However, to the best of our knowledge, there are no studies focusing on HFL. In addition, client selection for HFL faces more challenges than conventional FL, e.g., the time-varying connection of client-ES pairs and the limited budget of the Network Operator (NO). In this paper, we investigate a client selection problem for HFL, where the NO learns the number of successful participating clients to improve the training performance (i.e., select as many clients in each round) as well as under the limited budget on each ES. An online policy, called Context-aware Online Client Selection (COCS), is developed based on Contextual Combinatorial Multi-Armed Bandit (CC-MAB). COCS observes the side-information (context) of local computing and transmission of client-ES pairs and makes client selection decisions to maximize NO's utility given a limited budget. Theoretically, COCS achieves a sublinear regret compared to an Oracle policy on both strongly convex and non-convex HFL. Simulation results also support the efficiency of the proposed COCS policy on real-world datasets.

Jieming Bian, Zhu Fu, Jie Xu

Federated learning (FL), a popular decentralized and privacy-preserving machine learning (FL) framework, has received extensive research attention in recent years. The majority of existing works focus on supervised learning (SL) problems where it is assumed that clients carry labeled datasets while the server has no data. However, in realistic scenarios, clients are often unable to label their data due to the lack of expertise and motivation while the server may host a small amount of labeled data. How to reasonably utilize the server labeled data and the clients' unlabeled data is thus of paramount practical importance. In this paper, we propose a new FL algorithm, called FedSEAL, to solve this Semi-Supervised Federated Learning (SSFL) problem. Our algorithm utilizes self-ensemble learning and complementary negative learning to enhance both the accuracy and the efficiency of clients' unsupervised learning on unlabeled data, and orchestrates the model training on both the server side and the clients' side. Our experimental results on Fashion-MNIST and CIFAR10 datasets in the SSFL setting validate the effectiveness of our method, which outperforms the state-of-the-art SSFL methods by a large margin.

Jie Xu, Huayi Tang, Yazhou Ren et al.

Multi-view clustering can explore common semantics from multiple views and has attracted increasing attention. However, existing works punish multiple objectives in the same feature space, where they ignore the conflict between learning consistent common semantics and reconstructing inconsistent view-private information. In this paper, we propose a new framework of multi-level feature learning for contrastive multi-view clustering to address the aforementioned issue. Our method learns different levels of features from the raw features, including low-level features, high-level features, and semantic labels/features in a fusion-free manner, so that it can effectively achieve the reconstruction objective and the consistency objectives in different feature spaces. Specifically, the reconstruction objective is conducted on the low-level features. Two consistency objectives based on contrastive learning are conducted on the high-level features and the semantic labels, respectively. They make the high-level features effectively explore the common semantics and the semantic labels achieve the multi-view clustering. As a result, the proposed framework can reduce the adverse influence of view-private information. Extensive experiments on public datasets demonstrate that our method achieves state-of-the-art clustering effectiveness.

Zhe Qu, Shangqing Zhao, Jie Xu et al.

We revisit the traditional framework of wireless secret key generation, where two parties leverage the wireless channel randomness to establish a secret key. The essence in the framework is to quantify channel randomness into bit sequences for key generation. Conducting randomness tests on such bit sequences has been a common practice to provide the confidence to validate whether they are random. Interestingly, despite different settings in the tests, existing studies interpret the results the same: passing tests means that the bit sequences are indeed random. In this paper, we investigate how to properly test the wireless channel randomness to ensure enough security strength and key generation efficiency. In particular, we define an adversary model that leverages the imperfect randomness of the wireless channel to search the generated key, and create a guideline to set up randomness testing and privacy amplification to eliminate security loss and achieve efficient key generation rate. We use theoretical analysis and comprehensive experiments to reveal that common practice misuses randomness testing and privacy amplification: (i) no security insurance of key strength, (ii) low efficiency of key generation rate. After revision by our guideline, security loss can be eliminated and key generation rate can be increased significantly.

Cong Shen, Jie Xu, Sihui Zheng et al.

We advocate a new resource allocation framework, which we term resource rationing, for wireless federated learning (FL). Unlike existing resource allocation methods for FL, resource rationing focuses on balancing resources across learning rounds so that their collective impact on the federated learning performance is explicitly captured. This new framework can be integrated seamlessly with existing resource allocation schemes to optimize the convergence of FL. In particular, a novel "later-is-better" principle is at the front and center of resource rationing, which is validated empirically in several instances of wireless FL. We also point out technical challenges and research opportunities that are worth pursuing. Resource rationing highlights the benefits of treating the emerging FL as a new class of service that has its own characteristics, and designing communication algorithms for this particular service.

Letian Zhang, Lixing Chen, Jie Xu

Recent breakthroughs in deep learning (DL) have led to the emergence of many intelligent mobile applications and services, but in the meanwhile also pose unprecedented computing challenges on resource-constrained mobile devices. This paper builds a collaborative deep inference system between a resource-constrained mobile device and a powerful edge server, aiming at joining the power of both on-device processing and computation offloading. The basic idea of this system is to partition a deep neural network (DNN) into a front-end part running on the mobile device and a back-end part running on the edge server, with the key challenge being how to locate the optimal partition point to minimize the end-to-end inference delay. Unlike existing efforts on DNN partitioning that rely heavily on a dedicated offline profiling stage to search for the optimal partition point, our system has a built-in online learning module, called Autodidactic Neurosurgeon (ANS), to automatically learn the optimal partition point on-the-fly. Therefore, ANS is able to closely follow the changes of the system environment by generating new knowledge for adaptive decision making. The core of ANS is a novel contextual bandit learning algorithm, called $μ$LinUCB, which not only has provable theoretical learning performance guarantee but also is ultra-lightweight for easy real-world implementation. We implement our system on a video stream object detection testbed to validate the design of ANS and evaluate its performance. The experiments show that ANS significantly outperforms state-of-the-art benchmarks in terms of tracking system changes and reducing the end-to-end inference delay.

Jie Xu, Heqiang Wang, Lixing Chen

This paper studies a federated learning (FL) system, where \textit{multiple} FL services co-exist in a wireless network and share common wireless resources. It fills the void of wireless resource allocation for multiple simultaneous FL services in the existing literature. Our method designs a two-level resource allocation framework comprising \emph{intra-service} resource allocation and \emph{inter-service} resource allocation. The intra-service resource allocation problem aims to minimize the length of FL rounds by optimizing the bandwidth allocation among the clients of each FL service. Based on this, an inter-service resource allocation problem is further considered, which distributes bandwidth resources among multiple simultaneous FL services. We consider both cooperative and selfish providers of the FL services. For cooperative FL service providers, we design a distributed bandwidth allocation algorithm to optimize the overall performance of multiple FL services, meanwhile cater to the fairness among FL services and the privacy of clients. For selfish FL service providers, a new auction scheme is designed with the FL service owners as the bidders and the network provider as the auctioneer. The designed auction scheme strikes a balance between the overall FL performance and fairness. Our simulation results show that the proposed algorithms outperform other benchmarks under various network conditions.

Zhengping Luo, Shangqing Zhao, Zhuo Lu et al.

As Internet of Things (IoT) has emerged as the next logical stage of the Internet, it has become imperative to understand the vulnerabilities of the IoT systems when supporting diverse applications. Because machine learning has been applied in many IoT systems, the security implications of machine learning need to be studied following an adversarial machine learning approach. In this paper, we propose an adversarial machine learning based partial-model attack in the data fusion/aggregation process of IoT by only controlling a small part of the sensing devices. Our numerical results demonstrate the feasibility of this attack to disrupt the decision making in data fusion with limited control of IoT devices, e.g., the attack success rate reaches 83\% when the adversary tampers with only 8 out of 20 IoT devices. These results show that the machine learning engine of IoT system is highly vulnerable to attacks even when the adversary manipulates a small portion of IoT devices, and the outcome of these attacks severely disrupts IoT system operations.

Jie Xu, Heqiang Wang

This paper studies federated learning (FL) in a classic wireless network, where learning clients share a common wireless link to a coordinating server to perform federated model training using their local data. In such wireless federated learning networks (WFLNs), optimizing the learning performance depends crucially on how clients are selected and how bandwidth is allocated among the selected clients in every learning round, as both radio and client energy resources are limited. While existing works have made some attempts to allocate the limited wireless resources to optimize FL, they focus on the problem in individual learning rounds, overlooking an inherent yet critical feature of federated learning. This paper brings a new long-term perspective to resource allocation in WFLNs, realizing that learning rounds are not only temporally interdependent but also have varying significance towards the final learning outcome. To this end, we first design data-driven experiments to show that different temporal client selection patterns lead to considerably different learning performance. With the obtained insights, we formulate a stochastic optimization problem for joint client selection and bandwidth allocation under long-term client energy constraints, and develop a new algorithm that utilizes only currently available wireless channel information but can achieve long-term performance guarantee. Further experiments show that our algorithm results in the desired temporal client selection pattern, is adaptive to changing network environments and far outperforms benchmarks that ignore the long-term effect of FL.

Xiaoran Cai, Xiaopeng Mo, Junyang Chen et al.

Mobile edge learning is an emerging technique that enables distributed edge devices to collaborate in training shared machine learning models by exploiting their local data samples and communication and computation resources. To deal with the straggler dilemma issue faced in this technique, this paper proposes a new device to device enabled data sharing approach, in which different edge devices share their data samples among each other over communication links, in order to properly adjust their computation loads for increasing the training speed. Under this setup, we optimize the radio resource allocation for both data sharing and distributed training, with the objective of minimizing the total training delay under fixed numbers of local and global iterations. Numerical results show that the proposed data sharing design significantly reduces the training delay, and also enhances the training accuracy when the data samples are non independent and identically distributed among edge devices.

Mengwei Yang, Linqi Song, Jie Xu et al.

Privacy has raised considerable concerns recently, especially with the advent of information explosion and numerous data mining techniques to explore the information inside large volumes of data. In this context, a new distributed learning paradigm termed federated learning becomes prominent recently to tackle the privacy issues in distributed learning, where only learning models will be transmitted from the distributed nodes to servers without revealing users' own data and hence protecting the privacy of users. In this paper, we propose a horizontal federated XGBoost algorithm to solve the federated anomaly detection problem, where the anomaly detection aims to identify abnormalities from extremely unbalanced datasets and can be considered as a special classification problem. Our proposed federated XGBoost algorithm incorporates data aggregation and sparse federated update processes to balance the tradeoff between privacy and learning performance. In particular, we introduce the virtual data sample by aggregating a group of users' data together at a single distributed node. We compute parameters based on these virtual data samples in the local nodes and aggregate the learning model in the central server. In the learning model upgrading process, we focus more on the wrongly classified data before in the virtual sample and hence to generate sparse learning model parameters. By carefully controlling the size of these groups of samples, we can achieve a tradeoff between privacy and learning performance. Our experimental results show the effectiveness of our proposed scheme by comparing with existing state-of-the-arts.

Zhengping Luo, Shangqing Zhao, Zhuo Lu et al.

Defense strategies have been well studied to combat Byzantine attacks that aim to disrupt cooperative spectrum sensing by sending falsified versions of spectrum sensing data to a fusion center. However, existing studies usually assume network or attackers as passive entities, e.g., assuming the prior knowledge of attacks is known or fixed. In practice, attackers can actively adopt arbitrary behaviors and avoid pre-assumed patterns or assumptions used by defense strategies. In this paper, we revisit this security vulnerability as an adversarial machine learning problem and propose a novel learning-empowered attack framework named Learning-Evaluation-Beating (LEB) to mislead the fusion center. Based on the black-box nature of the fusion center in cooperative spectrum sensing, our new perspective is to make the adversarial use of machine learning to construct a surrogate model of the fusion center's decision model. We propose a generic algorithm to create malicious sensing data using this surrogate model. Our real-world experiments show that the LEB attack is effective to beat a wide range of existing defense strategies with an up to 82% of success ratio. Given the gap between the proposed LEB attack and existing defenses, we introduce a non-invasive method named as influence-limiting defense, which can coexist with existing defenses to defend against LEB attack or other similar attacks. We show that this defense is highly effective and reduces the overall disruption ratio of LEB attack by up to 80%.

Lixing Chen, Jie Xu, Shaolei Ren et al.

Shared edge computing platforms deployed at the radio access network are expected to significantly improve quality of service delivered by Application Service Providers (ASPs) in a flexible and economic way. However, placing edge service in every possible edge site by an ASP is practically infeasible due to the ASP's prohibitive budget requirement. In this paper, we investigate the edge service placement problem of an ASP under a limited budget, where the ASP dynamically rents computing/storage resources in edge sites to host its applications in close proximity to end users. Since the benefit of placing edge service in a specific site is usually unknown to the ASP a priori, optimal placement decisions must be made while learning this benefit. We pose this problem as a novel combinatorial contextual bandit learning problem. It is "combinatorial" because only a limited number of edge sites can be rented to provide the edge service given the ASP's budget. It is "contextual" because we utilize user context information to enable finer-grained learning and decision making. To solve this problem and optimize the edge computing performance, we propose SEEN, a Spatial-temporal Edge sErvice placemeNt algorithm. Furthermore, SEEN is extended to scenarios with overlapping service coverage by incorporating a disjunctively constrained knapsack problem. In both cases, we prove that our algorithm achieves a sublinear regret bound when it is compared to an oracle algorithm that knows the exact benefit information. Simulations are carried out on a real-world dataset, whose results show that SEEN significantly outperforms benchmark solutions.

Zihao Liu, Tao Liu, Wujie Wen et al.

As one of most fascinating machine learning techniques, deep neural network (DNN) has demonstrated excellent performance in various intelligent tasks such as image classification. DNN achieves such performance, to a large extent, by performing expensive training over huge volumes of training data. To reduce the data storage and transfer overhead in smart resource-limited Internet-of-Thing (IoT) systems, effective data compression is a "must-have" feature before transferring real-time produced dataset for training or classification. While there have been many well-known image compression approaches (such as JPEG), we for the first time find that a human-visual based image compression approach such as JPEG compression is not an optimized solution for DNN systems, especially with high compression ratios. To this end, we develop an image compression framework tailored for DNN applications, named "DeepN-JPEG", to embrace the nature of deep cascaded information process mechanism of DNN architecture. Extensive experiments, based on "ImageNet" dataset with various state-of-the-art DNNs, show that "DeepN-JPEG" can achieve ~3.5x higher compression rate over the popular JPEG solution while maintaining the same accuracy level for image recognition, demonstrating its great potential of storage and power efficiency in DNN-based smart IoT system design.

Jie Xu, Lixing Chen, Shaolei Ren

Mobile edge computing (a.k.a. fog computing) has recently emerged to enable in-situ processing of delay-sensitive applications at the edge of mobile networks. Providing grid power supply in support of mobile edge computing, however, is costly and even infeasible (in certain rugged or under-developed areas), thus mandating on-site renewable energy as a major or even sole power supply in increasingly many scenarios. Nonetheless, the high intermittency and unpredictability of renewable energy make it very challenging to deliver a high quality of service to users in energy harvesting mobile edge computing systems. In this paper, we address the challenge of incorporating renewables into mobile edge computing and propose an efficient reinforcement learning-based resource management algorithm, which learns on-the-fly the optimal policy of dynamic workload offloading (to the centralized cloud) and edge server provisioning to minimize the long-term system cost (including both service delay and operational cost). Our online learning algorithm uses a decomposition of the (offline) value iteration and (online) reinforcement learning, thus achieving a significant improvement of learning rate and run-time performance when compared to standard reinforcement learning algorithms such as Q-learning. We prove the convergence of the proposed algorithm and analytically show that the learned policy has a simple monotone structure amenable to practical implementation. Our simulation results validate the efficacy of our algorithm, which significantly improves the edge computing performance compared to fixed or myopic optimization schemes and conventional reinforcement learning algorithms.

Linqi Song, Jie Xu

Contextual bandit algorithms -- a class of multi-armed bandit algorithms that exploit the contextual information -- have been shown to be effective in solving sequential decision making problems under uncertainty. A common assumption adopted in the literature is that the realized (ground truth) reward by taking the selected action is observed by the learner at no cost, which, however, is not realistic in many practical scenarios. When observing the ground truth reward is costly, a key challenge for the learner is how to judiciously acquire the ground truth by assessing the benefits and costs in order to balance learning efficiency and learning cost. From the information theoretic perspective, a perhaps even more interesting question is how much efficiency might be lost due to this cost. In this paper, we design a novel contextual bandit-based learning algorithm and endow it with the active learning capability. The key feature of our algorithm is that in addition to sending a query to an annotator for the ground truth, prior information about the ground truth learned by the learner is sent together, thereby reducing the query cost. We prove that by carefully choosing the algorithm parameters, the learning regret of the proposed algorithm achieves the same order as that of conventional contextual bandit algorithms in cost-free scenarios, implying that, surprisingly, cost due to acquiring the ground truth does not increase the learning regret in the long-run. Our analysis shows that prior information about the ground truth plays a critical role in improving the system performance in scenarios where active learning is necessary.

Jie Xu, Tianwei Xing, Mihaela van der Schaar

Given the variability in student learning it is becoming increasingly important to tailor courses as well as course sequences to student needs. This paper presents a systematic methodology for offering personalized course sequence recommendations to students. First, a forward-search backward-induction algorithm is developed that can optimally select course sequences to decrease the time required for a student to graduate. The algorithm accounts for prerequisite requirements (typically present in higher level education) and course availability. Second, using the tools of multi-armed bandits, an algorithm is developed that can optimally recommend a course sequence that both reduces the time to graduate while also increasing the overall GPA of the student. The algorithm dynamically learns how students with different contextual backgrounds perform for given course sequences and then recommends an optimal course sequence for new students. Using real-world student data from the UCLA Mechanical and Aerospace Engineering department, we illustrate how the proposed algorithms outperform other methods that do not include student contextual information when making course sequence recommendations.

Yannick Meier, Jie Xu, Onur Atan et al.

To increase efficacy in traditional classroom courses as well as in Massive Open Online Courses (MOOCs), automated systems supporting the instructor are needed. One important problem is to automatically detect students that are going to do poorly in a course early enough to be able to take remedial actions. Existing grade prediction systems focus on maximizing the accuracy of the prediction while overseeing the importance of issuing timely and personalized predictions. This paper proposes an algorithm that predicts the final grade of each student in a class. It issues a prediction for each student individually, when the expected accuracy of the prediction is sufficient. The algorithm learns online what is the optimal prediction and time to issue a prediction based on past history of students' performance in a course. We derive a confidence estimate for the prediction accuracy and demonstrate the performance of our algorithm on a dataset obtained based on the performance of approximately 700 UCLA undergraduate students who have taken an introductory digital signal processing over the past 7 years. We demonstrate that for 85% of the students we can predict with 76% accuracy whether they are going do well or poorly in the class after the 4th course week. Using data obtained from a pilot course, our methodology suggests that it is effective to perform early in-class assessments such as quizzes, which result in timely performance prediction for each student, thereby enabling timely interventions by the instructor (at the student or class level) when necessary.

Jie Xu, Mihaela van der Schaar, Jiangchuan Liu et al.

This paper presents a systematic online prediction method (Social-Forecast) that is capable to accurately forecast the popularity of videos promoted by social media. Social-Forecast explicitly considers the dynamically changing and evolving propagation patterns of videos in social media when making popularity forecasts, thereby being situation and context aware. Social-Forecast aims to maximize the forecast reward, which is defined as a tradeoff between the popularity prediction accuracy and the timeliness with which a prediction is issued. The forecasting is performed online and requires no training phase or a priori knowledge. We analytically bound the prediction performance loss of Social-Forecast as compared to that obtained by an omniscient oracle and prove that the bound is sublinear in the number of video arrivals, thereby guaranteeing its short-term performance as well as its asymptotic convergence to the optimal performance. In addition, we conduct extensive experiments using real-world data traces collected from the videos shared in RenRen, one of the largest online social networks in China. These experiments show that our proposed method outperforms existing view-based approaches for popularity prediction (which are not context-aware) by more than 30% in terms of prediction rewards.