Junfan Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Junfan Li has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Shizhong Liao
Tianjin University
4 shared publications - Jie Liu
Harbin Institute of Technology, Shenzhen, China
2 shared publications - Zenglin Xu
Shanghai Academy of AI for Science Shanghai China
2 shared publications - Zheshun Wu
School of computer science and technology, Harbin Institute of Technology shenzhen, Shenzhen, China
2 shared publications - Dun Zeng
Department of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Sumei Sun
Agency for Science, Technology and Research (A*STAR)
1 shared publication
Latest Publications
- 4 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 1992-2007
Online Optimization for Learning to Communicate Over Time-Correlated Channels
Machine learning techniques have garnered great interest in designing communication systems owing to their capacity in tackling with channel uncertainty. To provide theoretical guarantees for learning-based communication systems, some recent works analyze generalization bounds for devised methods based on the assumption of Independently and Identically Distributed (I.I.D.) channels, a condition rarely met in practical scenarios. In this article, we drop the I.I.D. channel assumption and study an online optimization problem of learning to communicate over time-correlated channels. To address this issue, we further focus on two specific tasks: optimizing channel decoders for time-correlated fading channels and selecting optimal codebooks for time-correlated additive noise channels. For utilizing temporal dependence of considered channels to better learn communication systems, we develop two online optimization algorithms based on the optimistic online mirror descent framework. Furthermore, we provide theoretical guarantees for proposed algorithms via deriving sub-linear regret bound on the expected error probability of learned systems. Extensive simulation experiments have been conducted to validate that our presented approaches can leverage the channel correlation to achieve a lower average symbol error rate compared to baseline methods, consistent with our theoretical findings.
- 4 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 1992-2007
Online Optimization for Learning to Communicate Over Time-Correlated Channels
Machine learning techniques have garnered great interest in designing communication systems owing to their capacity in tackling with channel uncertainty. To provide theoretical guarantees for learning-based communication systems, some recent works analyze generalization bounds for devised methods based on the assumption of Independently and Identically Distributed (I.I.D.) channels, a condition rarely met in practical scenarios. In this article, we drop the I.I.D. channel assumption and study an online optimization problem of learning to communicate over time-correlated channels. To address this issue, we further focus on two specific tasks: optimizing channel decoders for time-correlated fading channels and selecting optimal codebooks for time-correlated additive noise channels. For utilizing temporal dependence of considered channels to better learn communication systems, we develop two online optimization algorithms based on the optimistic online mirror descent framework. Furthermore, we provide theoretical guarantees for proposed algorithms via deriving sub-linear regret bound on the expected error probability of learned systems. Extensive simulation experiments have been conducted to validate that our presented approaches can leverage the channel correlation to achieve a lower average symbol error rate compared to baseline methods, consistent with our theoretical findings.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (8) , 12201-12206
Topology Learning for Heterogeneous Decentralized Federated Learning Over Unreliable D2D Networks
With the proliferation of intelligent mobile devices in wireless device-to-device (D2D) networks, decentralized federated learning (DFL) has attracted significant interest. Compared to centralized federated learning (CFL), DFL mitigates the risk of central server failures due to communication bottlenecks. However, DFL faces several challenges, such as the severe heterogeneity of data distributions in diverse environments, and the transmission outages and package errors caused by the adoption of the User Datagram Protocol (UDP) in D2D networks. These challenges often degrade the convergence of training DFL models. To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound. By defining a novel quantity named unreliable links-aware neighborhood discrepancy in this convergence bound, we formulate a tractable optimization objective, and develop a novel Topology Learning method considering the Representation Discrepancy and Unreliable Links in DFL, named ToLRDUL. Intensive experiments under both feature skew and label skew settings have validated the effectiveness of our proposed method, demonstrating improved convergence speed and test accuracy, consistent with our theoretical findings.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (8) , 12201-12206
Topology Learning for Heterogeneous Decentralized Federated Learning Over Unreliable D2D Networks
With the proliferation of intelligent mobile devices in wireless device-to-device (D2D) networks, decentralized federated learning (DFL) has attracted significant interest. Compared to centralized federated learning (CFL), DFL mitigates the risk of central server failures due to communication bottlenecks. However, DFL faces several challenges, such as the severe heterogeneity of data distributions in diverse environments, and the transmission outages and package errors caused by the adoption of the User Datagram Protocol (UDP) in D2D networks. These challenges often degrade the convergence of training DFL models. To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound. By defining a novel quantity named unreliable links-aware neighborhood discrepancy in this convergence bound, we formulate a tractable optimization objective, and develop a novel Topology Learning method considering the Representation Discrepancy and Unreliable Links in DFL, named ToLRDUL. Intensive experiments under both feature skew and label skew settings have validated the effectiveness of our proposed method, demonstrating improved convergence speed and test accuracy, consistent with our theoretical findings.
- 17 March 2023
- Published by Springer Nature
- p. 333-348
Improved Regret Bounds for Online Kernel Selection Under Bandit Feedback
- 17 March 2023
- Published by Springer Nature
- p. 333-348
Improved Regret Bounds for Online Kernel Selection Under Bandit Feedback
- 10 September 2021
- Published by Springer Nature
- p. 67-83
High-Probability Kernel Alignment Regret Bounds for Online Kernel Selection
- 10 September 2021
- Published by Springer Nature
- p. 67-83
High-Probability Kernel Alignment Regret Bounds for Online Kernel Selection
- 1 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A New Learning Algorithm with General Loss for Neural Networks with Random Weights
Neural networks with random weights (NNRWs) which randomly assign weights to new hidden nodes, provide a new and promising stochastic approach for the research of neural networks, and have been proved to enjoy the universal approximation property. However, the design of existing learning algorithms for NNRWs is only based on the square loss function, which hinders the development of NNRWs. For strictly convex and strongly convex loss functions, it is unclear how to design learning algorithms, and what the convergence rates are. In this paper, we answer the qu estions affirmatively. First, we propose a new supervisory mechanism for constructing NNRWs, and prove the universal approximation property. Then we design a new learning algorithm and analyze the convergence rates of the algorithm, based on which the time complexities are also analyzed. !o be specific, the proposed algorithm enjoys sublinear convergence for smooth and strictly convex loss functions, and linear convergence for smooth and strongly convex loss functions. Finally, experimental results on several real-world datasets verify the convergence rates of the algorithm with different loss functions.
- 1 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A New Learning Algorithm with General Loss for Neural Networks with Random Weights
Neural networks with random weights (NNRWs) which randomly assign weights to new hidden nodes, provide a new and promising stochastic approach for the research of neural networks, and have been proved to enjoy the universal approximation property. However, the design of existing learning algorithms for NNRWs is only based on the square loss function, which hinders the development of NNRWs. For strictly convex and strongly convex loss functions, it is unclear how to design learning algorithms, and what the convergence rates are. In this paper, we answer the qu estions affirmatively. First, we propose a new supervisory mechanism for constructing NNRWs, and prove the universal approximation property. Then we design a new learning algorithm and analyze the convergence rates of the algorithm, based on which the time complexities are also analyzed. !o be specific, the proposed algorithm enjoys sublinear convergence for smooth and strictly convex loss functions, and linear convergence for smooth and strongly convex loss functions. Finally, experimental results on several real-world datasets verify the convergence rates of the algorithm with different loss functions.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 682-689
Online Kernel Selection via Grouped Adversarial Bandit Model
We study kernel selection for online kernel learning, also known as online kernel selection which can be treated as a sequential decision problem and thus must balance the regret and the time complexity. Existing online kernel selection approaches via expert advice and classical adversarial bandit model can not meet the issue. In this work, we propose a novel grouped adversarial bandit solution to the problem. We first correspond each candidate kernel to a basic arm of an adversarial bandit problem. Then, all of the kernels are divided into several groups where each group is abstracted as a super arm. At each round, we choose a super arm and a basic kernel within the selected super arm, and make prediction by an online kernel learning algorithm. Besides, we introduce a Bernoulli random variable to decide whether to choose all of the rest super arms. Theoretical analysis shows the proposed approach balances the regret and the time complexity explicitly, which could enjoy better pseudo-regret and high probability regret bound than classical adversarial bandit model and lighter time complexity than expert advice model. Experimental results on benchmark datasets verify that the proposed approach balances the efficiency and effectiveness better.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 682-689
Online Kernel Selection via Grouped Adversarial Bandit Model
We study kernel selection for online kernel learning, also known as online kernel selection which can be treated as a sequential decision problem and thus must balance the regret and the time complexity. Existing online kernel selection approaches via expert advice and classical adversarial bandit model can not meet the issue. In this work, we propose a novel grouped adversarial bandit solution to the problem. We first correspond each candidate kernel to a basic arm of an adversarial bandit problem. Then, all of the kernels are divided into several groups where each group is abstracted as a super arm. At each round, we choose a super arm and a basic kernel within the selected super arm, and make prediction by an online kernel learning algorithm. Besides, we introduce a Bernoulli random variable to decide whether to choose all of the rest super arms. Theoretical analysis shows the proposed approach balances the regret and the time complexity explicitly, which could enjoy better pseudo-regret and high probability regret bound than classical adversarial bandit model and lighter time complexity than expert advice model. Experimental results on benchmark datasets verify that the proposed approach balances the efficiency and effectiveness better.