5 papers
From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
Xinghao Wu, Jianwei Niu, Guogang Zhu +3
Heterogeneous federated learning (HtFL) aims to enable collaboration among clients that differ in both data distributions and model architectures. Prototype-based methods, which co…
Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
Xinghao Wu, Jianwei Niu, Xuefeng Liu +4
Federated Prototype Learning (FedPL) has emerged as an effective strategy for handling data heterogeneity in Federated Learning (FL). In FedPL, clients collaboratively construct a…
The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective
Guogang Zhu, Xuefeng Liu, Jianwei Niu +2
It is often observed that the aggregated model in FL underperforms on local data until after several rounds of local training. This temporary performance drop can potentially slow…
DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations
Guogang Zhu, Xuefeng Liu, Jianwei Niu +3
In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to t…
Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition
Xinghao Wu, Xuefeng Liu, Jianwei Niu +4
To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as t…