2 papers
cs.LG2026
Comprehensive and Reliable Feature Attribution for Diverse Modalities and Models via Frequency-Domain Insights
Zechen Liu, Feiyang Zhang, Wei Song +2
Personalized Federal learning(PFL) allows clients to cooperatively train a personalized model without disclosing their private dataset. However, PFL suffers from Non-IID, heterogen…
cs.LG2025
Fast Fourier Correlation is a Highly Efficient and Accurate Feature Attribution Algorithm from the Perspective of Control Theory and Game Theory
Zechen Liu, Feiyang Zhang, Wei Song +2
The study of neural networks from the perspective of Fourier features has garnered significant attention. While existing analytical research suggests that neural networks tend to l…