Author

Liyang Yuan

h-index 0 View on Semantic Scholar

We have 2 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Jul 2026

SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity

This work revisits client drift from a novel frequency-domain perspective and uncovers a critical Spectral Bias of Drift: inter-client gradient divergence is predominantly concentrated in low-frequency components which encode client-specific distributional shifts, while high-frequency components representing fine-grained features remain relatively consistent.

Liyang Yuan, Yibo Yang, Dandan Guo et al. · 0 citations

Preprint Jul 2026

FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering

Experimental evidence from a new perspective, the frequency domain, for SAM perturbations in federated settings is provided, revealing that inter-client perturbation inconsistencies are predominantly concentrated in the low-frequency spectrum.

Liyang Yuan, Yibo Yang, Dandan Guo · 0 citations