Zhiyong Chen

Benshun Yin, Zhiyong Chen, Meixia Tao

As an edge intelligence algorithm for multi-device collaborative training, federated learning (FL) can reduce the communication burden but increase the computing load of wireless devices. In contrast, split learning (SL) can reduce the computing load of devices by using model splitting and assignment, but increase the communication burden to transmit intermediate results. In this paper, to exploit the advantages of FL and SL, we propose a hybrid federated split learning (HFSL) framework in wireless networks, which combines the multi-worker parallel update of FL and flexible splitting of SL. To reduce the computational idleness in model splitting, we design a parallel computing scheme for model splitting without label sharing, and theoretically analyze the influence of the delayed gradient caused by the scheme on the convergence speed. Aiming to obtain the trade-off between the training time and energy consumption, we optimize the splitting decision, the bandwidth and computing resource allocation. The optimization problem is multi-objective, and we thus propose a predictive generative adversarial network (GAN)-powered multi-objective optimization algorithm to obtain the Pareto front of the problem. Experimental results show that the proposed algorithm outperforms others in finding Pareto optimal solutions, and the solutions of the proposed HFSL dominate the solution of FL.

Ye Yuan, Ling Shi, Jun Liu et al.

Fueled by applications in sensor networks, these years have witnessed a surge of interest in distributed estimation and filtering. A new approach is hereby proposed for the Distributed Kalman Filter (DKF) by integrating a local covariance computation scheme. Compared to existing well-established DKF methods, the virtue of the present approach lies in accelerating the convergence of the state estimates to those of the Centralized Kalman Filter (CKF). Meanwhile, an algorithm is proposed that allows each node to compute the averaged measurement noise covariance matrix within a minimal discrete-time running steps in a distributed way. Both theoretical analysis and extensive numerical simulations are conducted to show the feasibility and superiority of the proposed method.

Milad M. Kazemi, Mohsen Zamani, Zhiyong Chen

This paper examines the structural controllability for a group of agents, called followers, connected to each other based on the consensus law under commands of multiple leaders, which are agents with superior capabilities, over a fixed communication topology. It is proved that the graph-theoretic sufficient and necessary condition for the set of followers to be structurally controllable under the leaders' commands is leader-follower connectivity of the associated graph topology. This shrinks to graph connectivity for the case of solo leader. In the approach, we explicitly put into account the dependence among the entries of the system matrices for a consensus network using the linear parameterization technique introduced in [1].

Lijun Zhu, Zhiyong Chen, David J. Hill et al.

The paper proposes a novel event-triggered control scheme for nonlinear systems based on the input-delay method. Specifically, the closed-loop system is associated with a pair of auxiliary input and output. The auxiliary output is defined as the derivative of the continuous-time input function, while the auxiliary input is defined as the input disturbance caused by the sampling or equivalently the integral of the auxiliary output over the sampling period. As a result, a cyclic mapping forms from the input to the output via the system dynamics and back from the output to the input via the integral. The event-triggering law is constructed to make the mapping contractive such that the stabilization is achieved and an easy-to-check Zeno-free condition is provided. With this idea, we develop a theorem for the event-triggered control of interconnected nonlinear systems which is employed to solve the event-triggered control for lower-triangular systems with dynamic uncertainties.

Lijun Zhu, Zhiyong Chen, Xi Chen et al.

This paper studies a stabilization problem for linear MIMO systems subject to external perturbation that further requires the closed-loop system render a specified gain from the external perturbation to the output. The problem arises from control of networked systems, in particular, robust output synchronization of heterogeneous linear MIMO multi-agent systems via output feedback/communication. We propose a new approach that converts a class of MIMO systems into a normal form via repeated singular value decomposition and prove that a stabilization controller with a specified external gain can be explicitly constructed for the normal form.Two scenarios with static state feedback and dynamic output feedback are investigated. By integrating the reference model and internal model techniques, the robust output synchronization problem for MIMO multi-agent systems is converted into a stabilization problem with a specified externalgain and solved by the developed approach.

Chayan Banerjee, Zhiyong Chen, Nasimul Noman

Actor-critic (AC) algorithms are a class of model-free deep reinforcement learning algorithms, which have proven their efficacy in diverse domains, especially in solving continuous control problems. Improvement of exploration (action entropy) and exploitation (expected return) using more efficient samples is a critical issue in AC algorithms. A basic strategy of a learning algorithm is to facilitate indiscriminately exploring all of the environment state space, as well as to encourage exploring rarely visited states rather than frequently visited one. Under this strategy, we propose a new method to boost exploration through an intrinsic reward, based on measurement of a state's novelty and the associated benefit of exploring the state (with regards to policy optimization), altogether called plausible novelty. With incentivized exploration of plausible novel states, an AC algorithm is able to improve its sample efficiency and hence training performance. The new method is verified by extensive simulations of continuous control tasks of MuJoCo environments on a variety of prominent off-policy AC algorithms.

Tong Wu, Zhiyong Chen, Meixia Tao et al.

Lightweight and efficient neural network models for deep joint source-channel coding (JSCC) are crucial for semantic communications. In this paper, we propose a novel JSCC architecture, named MambaJSCC, that achieves state-of-the-art performance with low computational and parameter overhead. MambaJSCC utilizes the visual state space model with channel adaptation (VSSM-CA) blocks as its backbone for transmitting images over wireless channels, where the VSSM-CA primarily consists of the generalized state space models (GSSM) and the zero-parameter, zero-computational channel adaptation method (CSI-ReST). We design the GSSM module, leveraging reversible matrix transformations to express generalized scan expanding operations, and theoretically prove that two GSSM modules can effectively capture global information. We discover that GSSM inherently possesses the ability to adapt to channels, a form of endogenous intelligence. Based on this, we design the CSI-ReST method, which injects channel state information (CSI) into the initial state of GSSM to utilize its native response, and into the residual state to mitigate CSI forgetting, enabling effective channel adaptation without introducing additional computational and parameter overhead. Experimental results show that MambaJSCC not only outperforms existing JSCC methods (e.g., SwinJSCC) across various scenarios but also significantly reduces parameter size, computational overhead, and inference delay.

Gewei Zuo, Lijun Zhu, Yujuan Wang et al.

A finite-time protocol for a multi-agent systems (MASs) can guarantee the convergence of every agent in a finite time interval in contrast to the asymptotic convergence, but the settling time depends on the initial condition and design parameters and is inconsistent across the agents. In this paper, we study the prescribed-time cooperative output regulation (PTCOR) problem for a class of linear heterogeneous MASs under a directed communication graph, where the settling time of every agent can be specified a priori and thus consistent. As a special case of PTCOR, the necessary and sufficient condition for prescribed-time output regulation of an individual system is first discussed. Then, the PTCOR problem is converted into two cascaded subsystem, where the first one composed of distributed estimate errors and local estimate errors and the second one is for local tracking errors. The criterion for prescribed-time stabilization of the cascaded system is proposed and is found to be different from that of traditional asymptotic stabilization of a cascaded system. Under the criterion and sufficient condition, the general PTCOR problem is studied in two scenarios including state feedback control and measurement output feedback control. In particular, a distributed prescribed-time observer for each subsystem is explicitly constructed to estimate the exosystem's state. Based on the observer, a distributed controller is proposed to achieve convergence of the regulated output to zero within a prescribed-time.

Jialun Cao, Zhiyong Chen, Jiarong Wu et al.

Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant imbalances. First, imbalanced programming language. 95.8% of benchmarks involve Python, while only 5 benchmarks involve Java. Second, imbalanced code granularity. Function-/statement-level benchmarks account for over 83.3% of benchmarks. Only a mere handful extends to class-/project-levels, and all are limited to Python. Third, lacking advanced features. Existing benchmarks primarily assess basic coding skills, while overlooking advanced Object-Oriented Programming (OOP) features (i.e., encapsulation, inheritance, and polymorphism). To fill these gaps, we propose JavaBench, a project-level Java benchmark that exercises OOP features. It comprises four Java projects with 389 methods in 106 Java classes. The test coverage is up to 92%, and JavaBench is attested by 282 undergraduate students, reaching a 90.93/100 average score (i.e., pass rate against the test suite), ensuring the quality of documentation, code skeleton, and tests. To better evaluate LLM's capability against JavaBench, we introduce a systematic evaluation design covering three context settings and five synthesis strategies at two granularities using three hierarchical metrics. Our extensive experiment yields several interesting findings. First, we noticed that regarding project-level Java programming, LLMs are far behind undergraduate students (no project can be correctly completed by any studied LLMs, and at most 41.17% Pass@5 in a more relaxed evaluation). Second, using method signature as prompt context may strike an ideal balance for project-level code generation. JavaBench is publicly available at https://github.com/java-bench/JavaBench.

Jiahui Liu, Zhenkun Cai, Zhiyong Chen et al.

Attention Graph Neural Networks (AT-GNNs), such as GAT and Graph Transformer, have demonstrated superior performance compared to other GNNs. However, existing GNN systems struggle to efficiently train AT-GNNs on GPUs due to their intricate computation patterns. The execution of AT-GNN operations without kernel fusion results in heavy data movement and significant kernel launch overhead, while fixed thread scheduling in existing GNN kernel fusion strategies leads to sub-optimal performance, redundant computation and unbalanced workload. To address these challenges, we propose a dynamic kernel fusion framework, DF-GNN, for the AT-GNN family. DF-GNN introduces a dynamic bi-level thread scheduling strategy, enabling flexible adjustments to thread scheduling while retaining the benefits of shared memory within the fused kernel. DF-GNN tailors specific thread scheduling for operations in AT-GNNs and considers the performance bottleneck shift caused by the presence of super nodes. Additionally, DF-GNN is integrated with the PyTorch framework for high programmability. Evaluations across diverse GNN models and multiple datasets reveal that DF-GNN surpasses existing GNN kernel optimization works like cuGraph and dgNN, with speedups up to $7.0\times$ over the state-of-the-art non-fusion DGL sparse library. Moreover, it achieves an average speedup of $2.16\times$ in end-to-end training compared to the popular GNN computing framework DGL.

Haohui Chen, Zhiyong Chen, Aoxiang Liu et al.

Deterministic policy gradient algorithms for continuous control suffer from value estimation biases that degrade performance. While double critics reduce such biases, the exploration potential of double actors remains underexplored. Building on temporal-difference error-driven regularization (TDDR), a double actor-critic framework, this work introduces enhanced methods to achieve flexible bias control and stronger representation learning. We propose three convex combination strategies, symmetric and asymmetric, that balance pessimistic estimates to mitigate overestimation and optimistic exploration via double actors to alleviate underestimation. A single hyperparameter governs this mechanism, enabling tunable control across the bias spectrum. To further improve performance, we integrate augmented state and action representations into the actor and critic networks. Extensive experiments show that our approach consistently outperforms benchmarks, demonstrating the value of tunable bias and revealing that both overestimation and underestimation can be exploited differently depending on the environment.

Zhiqi Ai, Meixuan Bao, Zhiyong Chen et al.

The performance of speaker verification systems is adversely affected by speaker aging. However, due to challenges in data collection, particularly the lack of sustained and large-scale longitudinal data for individuals, research on speaker aging remains difficult. In this paper, we present VoxAging, a large-scale longitudinal dataset collected from 293 speakers (226 English speakers and 67 Mandarin speakers) over several years, with the longest time span reaching 17 years (approximately 900 weeks). For each speaker, the data were recorded at weekly intervals. We studied the phenomenon of speaker aging and its effects on advanced speaker verification systems, analyzed individual speaker aging processes, and explored the impact of factors such as age group and gender on speaker aging research.

Zhongwei Wang, Tong Wu, Zhiyong Chen et al.

Federated semi-supervised learning (FSSL) is primarily challenged by two factors: the scarcity of labeled data across clients and the non-independent and identically distribution (non-IID) nature of data among clients. In this paper, we propose a novel approach, diffusion model-based data synthesis aided FSSL (DDSA-FSSL), which utilizes a diffusion model (DM) to generate synthetic data, bridging the gap between heterogeneous local data distributions and the global data distribution. In DDSA-FSSL, clients address the challenge of the scarcity of labeled data by employing a federated learning-trained classifier to perform pseudo labeling for unlabeled data. The DM is then collaboratively trained using both labeled and precision-optimized pseudo-labeled data, enabling clients to generate synthetic samples for classes that are absent in their labeled datasets. This process allows clients to generate more comprehensive synthetic datasets aligned with the global distribution. Extensive experiments conducted on multiple datasets and varying non-IID distributions demonstrate the effectiveness of DDSA-FSSL, e.g., it improves accuracy from 38.46% to 52.14% on CIFAR-10 datasets with 10% labeled data.

Zhiqi Ai, Zhiyong Chen, Shugong Xu

In this paper, we propose MM-KWS, a novel approach to user-defined keyword spotting leveraging multi-modal enrollments of text and speech templates. Unlike previous methods that focus solely on either text or speech features, MM-KWS extracts phoneme, text, and speech embeddings from both modalities. These embeddings are then compared with the query speech embedding to detect the target keywords. To ensure the applicability of MM-KWS across diverse languages, we utilize a feature extractor incorporating several multilingual pre-trained models. Subsequently, we validate its effectiveness on Mandarin and English tasks. In addition, we have integrated advanced data augmentation tools for hard case mining to enhance MM-KWS in distinguishing confusable words. Experimental results on the LibriPhrase and WenetPhrase datasets demonstrate that MM-KWS outperforms prior methods significantly.

Chayan Banerjee, Zhiyong Chen, Nasimul Noman

Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the policy). It has achieved state-of-the-art performance on a range of continuous-control benchmark tasks, outperforming prior on-policy and off-policy methods. SAC works in an off-policy fashion where data are sampled uniformly from past experiences (stored in a buffer) using which parameters of the policy and value function networks are updated. We propose certain crucial modifications for boosting the performance of SAC and make it more sample efficient. In our proposed improved SAC, we firstly introduce a new prioritization scheme for selecting better samples from the experience replay buffer. Secondly we use a mixture of the prioritized off-policy data with the latest on-policy data for training the policy and the value function networks. We compare our approach with the vanilla SAC and some recent variants of SAC and show that our approach outperforms the said algorithmic benchmarks. It is comparatively more stable and sample efficient when tested on a number of continuous control tasks in MuJoCo environments.

Zhiwei Jia, Shugong Xu, Shiyi Mu et al.

Although recent works based on deep learning have made progress in improving recognition accuracy on scene text recognition, how to handle low-quality text images in end-to-end deep networks remains a research challenge. In this paper, we propose an Iterative Fusion based Recognizer (IFR) for low quality scene text recognition, taking advantage of refined text images input and robust feature representation. IFR contains two branches which focus on scene text recognition and low quality scene text image recovery respectively. We utilize an iterative collaboration between two branches, which can effectively alleviate the impact of low quality input. A feature fusion module is proposed to strengthen the feature representation of the two branches, where the features from the Recognizer are Fused with image Restoration branch, referred to as RRF. Without changing the recognition network structure, extensive quantitative and qualitative experimental results show that the proposed method significantly outperforms the baseline methods in boosting the recognition accuracy of benchmark datasets and low resolution images in TextZoom dataset.

Zhiyong Chen, Zongze Ren, Shugong Xu

Learning a good speaker embedding is important for many automatic speaker recognition tasks, including verification, identification and diarization. The embeddings learned by softmax are not discriminative enough for open-set verification tasks. Angular based embedding learning target can achieve such discriminativeness by optimizing angular distance and adding margin penalty. We apply several different popular angular margin embedding learning strategies in this work and explicitly compare their performance on Voxceleb speaker recognition dataset. Observing the fact that encouraging inter-class separability is important when applying angular based embedding learning, we propose an exclusive inter-class regularization as a complement for angular based loss. We verify the effectiveness of these methods for learning a discriminative embedding space on ASV task with several experiments. These methods together, we manage to achieve an impressive result with 16.5% improvement on equal error rate (EER) and 18.2% improvement on minimum detection cost function comparing with baseline softmax systems.

Zongze Ren, Zhiyong Chen, Shugong Xu

Speaker embeddings become growing popular in the text-independent speaker verification task. In this paper, we propose two improvements during the training stage. The improvements are both based on triplet cause the training stage and the evaluation stage of the baseline x-vector system focus on different aims. Firstly, we introduce triplet loss for optimizing the Euclidean distances between embeddings while minimizing the multi-class cross entropy loss. Secondly, we design an embedding similarity measurement network for controlling the similarity between the two selected embeddings. We further jointly train the two new methods with the original network and achieve state-of-the-art. The multi-task training synergies are shown with a 9% reduction equal error rate (EER) and detected cost function (DCF) on the 2016 NIST Speaker Recognition Evaluation (SRE) Test Set.

Bin Liu, Zhiyong Chen, Hai-Tao Zhang et al.

A multi-unmanned surface vessel (USV) formation control system is established on a novel platform composed of three 1.2 meter-long hydraulic jet propulsion surface vessels, a differential GPS reference station, and inter-vessel Zigbee communication modules. The system is also equipped with an upper level collective multi-USV protocol and a lower level vessel dynamics controller. The system is capable of chasing and surrounding a target vessel. The results are supported by rigorous theoretical analysis in terms of asymptotical surrounding behavior and trajectory regulation. Extensive experiments are conducted to demonstrate the effectiveness and efficiency of the proposed hardware and software architectures.

Imil Hamda Imran, Zhiyong Chen, Lijun Zhu et al.

In traditional adaptive control, the certainty equivalence principle suggests a two-step design scheme. A controller is first designed for the ideal situation assuming the uncertain parameter was known and it renders a Lyapunov function. Then, the uncertain parameter in the controller is replaced by its estimation that is updated by an adaptive law along the gradient of Lyapunov function. This principle does not generally work for a multi-agent system as an adaptive law based on the gradient of (centrally constructed) Lyapunov function cannot be implemented in a distributed fashion, except for limited situations. In this paper, we propose a novel distributed adaptive scheme, not relying on gradient of Lyapunov function, for general multi-agent systems. In this scheme, asymptotic consensus of a second-order uncertain multi-agent system is achieved in a network of directed graph.

Wentuo Fang, Mohsen Zamani, Zhiyong Chen

This paper aims at secure and privacy preserving consensus algorithms of networked systems. Due to the technical challenges behind decentralized design of such algorithms, the existing results are mainly restricted to a network of systems with simplest first-order dynamics. Like many other control problems, breakthrough of the gap between first-order dynamics and higher-order ones demands for more advanced technical developments. In this paper, we explore a Paillier encryption based average consensus algorithm for a network of systems with second-order dynamics, with randomness added to network weights. The conditions for privacy preserving, especially depending on consensus rate, are thoroughly studied with theoretical analysis and numerical verification.