Comprehensive and Reliable Feature Attribution for Diverse Modalities and Models via Frequency-Domain Insights 事件

Comprehensive and Reliable Feature Attribution for Diverse Modalities and Models via Frequency-Domain Insights arXiv:2411.18343v3 Announce Type: replace-cross Abstract: Personalized Federal learning(PFL) allows clients to cooperatively train a personalized model without disclosing their private dataset. However, PFL suffers from Non-IID, heterogeneous devices, lack of fairness, and unclear contribution which urgently need the interpretability of deep learning model to overcome these challenges.