Publications
A collection of my research work.
SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning
Ran Tao, Qiugang Zhan, Shantian Yang, Xiurui Xie, Qi Tian, Guisong Liu
Proceedings of the AAAI Conference on Artificial Intelligence 2026
We propose SFedHIFI, a novel Spiking Federated Learning framework with Fire Rate-Based Heterogeneous Information Fusion. Specifically, SFedHIFI employs channel-wise matrix decomposition to deploy SNN models of adaptive complexity on clients with heterogeneous resources.
SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learning
Qiugang Zhan, Jinbo Cao, Xiurui Xie†, Huajin Tang, Malu Zhang, Shantian Yang, Guisong Liu†
IEEE Transactions on Neural Networks and Learning Systems 2025
We propose an active client selection method for spiking federated learning. This method assign credit for clients according to the firing intensity changes.
Flexible sharpness-aware personalized federated learning
Xinda Xing, Qiugang Zhan(共一), Xiurui Xie, Yuning Yang, Qiang Wang, Guisong Liu
Proceedings of the AAAI Conference on Artificial Intelligence 2025
We propose a simple and general PFL method, Federated learning with Flexible Sharpness-Aware Minimization (FedFSA). It emphasize the importance of applying a larger perturbation to critical layers of the local model when using the Sharpness-Aware Minimization (SAM) optimizer.
A two-stage spiking meta-learning method for few-shot classification
Qiugang Zhan, Bingchao Wang, Anning Jiang, Xiurui Xie, Malu Zhang, Guisong Liu†
Knowledge-Based Systems 2024
We explore a two-stage metric-based SNN meta-learning framework. During pre-training, a CESM model is trained to extract image features. In the meta-training stage, the MESM model employs the CKA method to measure the similarity between these learned features for meta-learning.
Spiking Transfer Learning From RGB Image to Neuromorphic Event Stream
Qiugang Zhan, Guisong Liu†, Xiurui Xie†, Ran Tao, Malu Zhang, Huajin Tang
IEEE Transactions on Image Processing 2024
To take advantage of both the rich knowledge in labeled RGB images and the features of the event camera, we propose a transfer learning method from the RGB to the event domain.
Federated learning for spiking neural networks by hint-layer knowledge distillation
Xiurui Xie, Jingxuan Feng, Guisong Liu†, Qiugang Zhan†, Zhetong Liu, Malu Zhang
Applied Soft Computing 2024
We propose a Hint-layer Distillation-based Spiking Federated Learning (HDSFL) framework that reduces the communication cost by transferring knowledge and losslessly compressing the spiking tensor.
Bio-inspired Active Learning method in spiking neural network
Qiugang Zhan, Guisong Liu†, Xiurui Xie†, Malu Zhang, Guolin Sun
Knowledge-Based Systems 2023
We propose an effective Bio-inspired Active Learning (BAL) method to reduce the training cost of SNN models. Bio-inspired behavior patterns of spiking neurons are defined to represent the internal states of SNN models for active learning.
Effective active learning method for spiking neural networks
Xiurui Xie, Bei Yu, Guisong Liu†, Qiugang Zhan, Huajin Tang
IEEE Transactions on Neural Networks and Learning Systems 2023
We propose an effective active learning method with a loss prediction module for a deep SNN model.
Effective Transfer Learning Algorithm in Spiking Neural Networks
Qiugang Zhan, Guisong Liu†, Xiurui Xie, Guolin Sun, Huajin Tang
IEEE Transactions on Cybernetics 2022
We propose the first transfer learning framework in SNN, and the rationality of centered kernel alignment (CKA) as a domain distance measurement relative to maximum mean discrepancy (MMD) in deep SNNs.