49 citations · 126 across the 13 of their papers we have counts for
7 papers · 1 filter
FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning
Lingzhi Gao, Zexi Li, Yang Lu +1
Personalized federated learning (pFL) enables collaborative training among multiple clients to enhance the capability of customized local models. In pFL, clients may have heterogen…
Understanding Prompt Tuning for V-L Models Through the Lens of Neural Collapse
Didi Zhu, Zexi Li, Min Zhang +6
Large-scale vision-language (V-L) models have demonstrated remarkable generalization capabilities for downstream tasks through prompt tuning. However, the mechanisms behind the lea…
Edge-cloud Collaborative Learning with Federated and Centralized Features
Zexi Li, Qunwei Li, Yi Zhou +3
Federated learning (FL) is a popular way of edge computing that doesn't compromise users' privacy. Current FL paradigms assume that data only resides on the edge, while cloud serve…
Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients
Chenrui Wu, Zexi Li, Fangxin Wang +1
Federated learning (FL) is a distributed framework for collaboratively training with privacy guarantees. In real-world scenarios, clients may have Non-IID data (local class imbalan…
Universal Domain Adaptation via Compressive Attention Matching
Didi Zhu, Yincuan Li, Junkun Yuan +3
Universal domain adaptation (UniDA) aims to transfer knowledge from the source domain to the target domain without any prior knowledge about the label set. The challenge lies in ho…
No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
Zexi Li, Xinyi Shang, Rui He +2
Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of local models as the ke…
Revisiting Weighted Aggregation in Federated Learning with Neural Networks
Zexi Li, Tao Lin, Xinyi Shang +1
In federated learning (FL), weighted aggregation of local models is conducted to generate a global model, and the aggregation weights are normalized (the sum of weights is 1) and p…