Qinglun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qinglun Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Li Shen
Shenzhen Campus of Sun Yat-sen University
4 shared publications - Quanjun Yin
College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China
4 shared publications - Miao Zhang
National University of Defense Technology
2 shared publications - Xiaochun Cao
Shenzhen Campus of Sun Yat-sen University
2 shared publications Chengyi Fang
1 shared publication- Dacheng Tao
Nanyang technological university, Singapore, Singapore
1 shared publication
Latest Publications
- 23 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
DFedSVRG: Decentralized federated learning with stochastic variance reduced gradient
- 23 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
DFedSVRG: Decentralized federated learning with stochastic variance reduced gradient
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-12
Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
Decentralized Federated Learning has emerged as an alternative to centralized architectures due to its faster training, privacy preservation, and reduced communication overhead. In decentralized communication, the server aggregation phase in Centralized Federated Learning shifts to the client side, which means that clients connect with each other in a peer-to-peer manner. However, compared to the centralized mode, data heterogeneity in Decentralized Federated Learning will cause larger variances between aggregated models, which leads to slow convergence in training and poor generalization performance in tests. To address these issues, we introduce Catalyst Acceleration and propose an acceleration Decentralized Federated Learning algorithm called DFedCata. It consists of two main components: the Moreau envelope function, which primarily addresses parameter inconsistencies among clients caused by data heterogeneity, and Nesterov's extrapolation step, which accelerates the aggregation phase. Theoretically, we prove the optimization error bound and generalization error bound of the algorithm, providing a further understanding of the nature of the algorithm and the theoretical perspectives on the hyperparameter choice. Empirically, we demonstrate the advantages of the proposed algorithm in both convergence speed, computational cost, and generalization performance on CIFAR10/100 and Tiny-ImageNet with various non-iid data distributions. Moreover, extensive experiments are conducted to validate the theoretical properties of DFedCata, showing strong consistency between theory and empirical observations. Our code is available at https://github.com/zzylyxx/DFedCata.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-12
Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
Decentralized Federated Learning has emerged as an alternative to centralized architectures due to its faster training, privacy preservation, and reduced communication overhead. In decentralized communication, the server aggregation phase in Centralized Federated Learning shifts to the client side, which means that clients connect with each other in a peer-to-peer manner. However, compared to the centralized mode, data heterogeneity in Decentralized Federated Learning will cause larger variances between aggregated models, which leads to slow convergence in training and poor generalization performance in tests. To address these issues, we introduce Catalyst Acceleration and propose an acceleration Decentralized Federated Learning algorithm called DFedCata. It consists of two main components: the Moreau envelope function, which primarily addresses parameter inconsistencies among clients caused by data heterogeneity, and Nesterov's extrapolation step, which accelerates the aggregation phase. Theoretically, we prove the optimization error bound and generalization error bound of the algorithm, providing a further understanding of the nature of the algorithm and the theoretical perspectives on the hyperparameter choice. Empirically, we demonstrate the advantages of the proposed algorithm in both convergence speed, computational cost, and generalization performance on CIFAR10/100 and Tiny-ImageNet with various non-iid data distributions. Moreover, extensive experiments are conducted to validate the theoretical properties of DFedCata, showing strong consistency between theory and empirical observations. Our code is available at https://github.com/zzylyxx/DFedCata.
- 9 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (8) , 2745-2756
Asymmetrically Decentralized Federated Learning
To address the communication burden and privacy concerns associated with the centralized server in Federated Learning (FL), Decentralized Federated Learning (DFL) has emerged, which discards the server with a peer-to-peer (P2P) communication framework, significantly expanding the application scenarios of FL. However, most existing DFL algorithms are based on symmetric topologies, such as ring and grid topology, which can easily lead to deadlocks and are susceptible to the impact of network link quality in practice. To address these issues, we propose DFedSGPSM, a transitional framework that converts symmetric DFL optimizers into asymmetric variants. By adopting the Push-Sum protocol in asymmetric network topologies, our framework successfully circumvents the deadlock and link-quality issues prevalent in symmetric configurations. To further validate the effectiveness of our algorithm framework, we integrate the local momentum (in DFedAvgM) and SAM (in DFedSAM) from existing symmetric DFL optimizer into DFedSGPSM to accelerate training and pursue smooth local minimum, which enables existing symmetric DFL optimizers to be seamlessly integrated into asymmetric DFL. Theoretical analysis proves that DFedSGPSM achieves a linear speedup rate of $\mathcal{O}(\frac{1}{\sqrt{nT}})$ in the non-convex setting. This analysis also reveals crucial issues such as tighter upper bounds achieved with improved topological connectivity. Empirically, extensive experiments conducted on the MNIST, CIFAR10&100 datasets demonstrate the superior performance of our proposed algorithm compared to several existing SOTA optimizers in terms of generalization.
- 9 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (8) , 2745-2756
Asymmetrically Decentralized Federated Learning
To address the communication burden and privacy concerns associated with the centralized server in Federated Learning (FL), Decentralized Federated Learning (DFL) has emerged, which discards the server with a peer-to-peer (P2P) communication framework, significantly expanding the application scenarios of FL. However, most existing DFL algorithms are based on symmetric topologies, such as ring and grid topology, which can easily lead to deadlocks and are susceptible to the impact of network link quality in practice. To address these issues, we propose DFedSGPSM, a transitional framework that converts symmetric DFL optimizers into asymmetric variants. By adopting the Push-Sum protocol in asymmetric network topologies, our framework successfully circumvents the deadlock and link-quality issues prevalent in symmetric configurations. To further validate the effectiveness of our algorithm framework, we integrate the local momentum (in DFedAvgM) and SAM (in DFedSAM) from existing symmetric DFL optimizer into DFedSGPSM to accelerate training and pursue smooth local minimum, which enables existing symmetric DFL optimizers to be seamlessly integrated into asymmetric DFL. Theoretical analysis proves that DFedSGPSM achieves a linear speedup rate of $\mathcal{O}(\frac{1}{\sqrt{nT}})$ in the non-convex setting. This analysis also reveals crucial issues such as tighter upper bounds achieved with improved topological connectivity. Empirically, extensive experiments conducted on the MNIST, CIFAR10&100 datasets demonstrate the superior performance of our proposed algorithm compared to several existing SOTA optimizers in terms of generalization.
- 28 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (6) , 4803-4815
DFedADMM: Dual Constraint Controlled Model Inconsistency for Decentralize Federated Learning
To address the communication burden issues associated with Federated Learning (FL), Decentralized Federated Learning (DFL) discards the central server and establishes a decentralized communication network, where each client communicates only with neighboring clients. However, existing DFL methods still suffer from two major challenges: local inconsistency and local heterogeneous overfitting, which existing DFL methods have not fundamentally addressed. To tackle these issues, we propose novel DFL algorithms, DFedADMM and its enhanced version DFedADMM-SAM, to improve the performance for DFL. The DFedADMM algorithm employs primal-dual optimization (ADMM) by utilizing dual variables to control the model inconsistency raised from the decentralized heterogeneous data distributions. The DFedADMM-SAM algorithm further improves on DFedADMM by employing a Sharpness-Aware Minimization (SAM) optimizer, which uses gradient perturbations to generate locally flat models and searches for models with uniformly low loss values to mitigate local heterogeneous overfitting. Theoretically, we derive convergence rates of$\mathcal {O}(\frac{1}{\sqrt{KT}}+\frac{1}{KT(1-\psi )^{2}})$ and$ \mathcal {O}(\frac{1}{\sqrt{KT}}+\frac{1}{KT(1-\psi )^{2}}+ \frac{1}{T^{3/2}K^{1/2}})$ in the non-convex setting for DFedADMM and DFedADMM-SAM, respectively, where$1 - \psi$ represents the spectral gap of the gossip matrix. Empirically, extensive experiments on MNIST, CIFAR10, and CIFAR100 datasets demonstrate that our algorithms exhibit superior performance in terms of generalization, convergence speed, and communication overhead compared to existing state-of-the-art (SOTA) optimizers in DFL.- 28 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (6) , 4803-4815
DFedADMM: Dual Constraint Controlled Model Inconsistency for Decentralize Federated Learning
To address the communication burden issues associated with Federated Learning (FL), Decentralized Federated Learning (DFL) discards the central server and establishes a decentralized communication network, where each client communicates only with neighboring clients. However, existing DFL methods still suffer from two major challenges: local inconsistency and local heterogeneous overfitting, which existing DFL methods have not fundamentally addressed. To tackle these issues, we propose novel DFL algorithms, DFedADMM and its enhanced version DFedADMM-SAM, to improve the performance for DFL. The DFedADMM algorithm employs primal-dual optimization (ADMM) by utilizing dual variables to control the model inconsistency raised from the decentralized heterogeneous data distributions. The DFedADMM-SAM algorithm further improves on DFedADMM by employing a Sharpness-Aware Minimization (SAM) optimizer, which uses gradient perturbations to generate locally flat models and searches for models with uniformly low loss values to mitigate local heterogeneous overfitting. Theoretically, we derive convergence rates of$\mathcal {O}(\frac{1}{\sqrt{KT}}+\frac{1}{KT(1-\psi )^{2}})$ and$ \mathcal {O}(\frac{1}{\sqrt{KT}}+\frac{1}{KT(1-\psi )^{2}}+ \frac{1}{T^{3/2}K^{1/2}})$ in the non-convex setting for DFedADMM and DFedADMM-SAM, respectively, where$1 - \psi$ represents the spectral gap of the gossip matrix. Empirically, extensive experiments on MNIST, CIFAR10, and CIFAR100 datasets demonstrate that our algorithms exhibit superior performance in terms of generalization, convergence speed, and communication overhead compared to existing state-of-the-art (SOTA) optimizers in DFL.- 30 December 2024
- Published by Elsevier in Neural Networks
- Vol. 184, 107084
DFedGFM: Pursuing global consistency for Decentralized Federated Learning via global flatness and global momentum
- 30 December 2024
- Published by Elsevier in Neural Networks
- Vol. 184, 107084
DFedGFM: Pursuing global consistency for Decentralized Federated Learning via global flatness and global momentum