activity
20242026
most citedFederated Continual Learning for Edge-AI: A Comprehensive Survey

6 citations · 6 across the 2 of their papers we have counts for

collaborators

10 papers

cs.LG2026

DeepFusion: Accelerating MoE Training via Federated Knowledge Distillation from Heterogeneous Edge Devices

Songyuan Li, Jia Hu, Ahmed M. Abdelmoniem +3

Recent Mixture-of-Experts (MoE)-based large language models (LLMs) such as Qwen-MoE and DeepSeek-MoE are transforming generative AI in natural language processing. However, these m…

cs.LG2025

Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection

Desong Zhang, Jia Hu, Geyong Min

Spiking Neural Networks (SNNs) process information via discrete spikes, enabling them to operate at remarkably low energy levels. However, our experimental observations reveal a st…

cs.LG2025

Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning

Feng Yu, Jia Hu, Geyong Min

Federated Parameter-Efficient Fine-Tuning (Fed-PEFT) enables lightweight adaptation of large pre-trained models in federated learning settings by updating only a small subset of pa…

cs.LG2025

Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation

Fei Wu, Jia Hu, Geyong Min +1

Driven by the rapid growth of model parameters, parameter-efficient fine-tuning (PEFT) has become essential for adapting large models to diverse downstream tasks under constrained…

cs.DC2025

Zero-Knowledge Proof-Based Consensus for Blockchain-Secured Federated Learning

Tianxing Fu, Jia Hu, Geyong Min +1

Federated learning (FL) enables multiple participants to collaboratively train machine learning models while ensuring their data remains private and secure. Blockchain technology f…

cs.LG2025

Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edge

Songyuan Li, Jia Hu, Geyong Min +1

Foundation models (FMs) such as GPT-4 exhibit exceptional generative capabilities across diverse downstream tasks through fine-tuning. Split Federated Learning (SFL) facilitates pr…