AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Generalizable Heterogeneity-aware Federated Feature and Basic-matrix Consistency Learning

Xuan Lai, Luying Zhong, Tianying Lu, Junjie Zhang, Zhiqin Huang, Zheyi Chen

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add FIA feature alignment on public data to local training (ablation)local baseline · Digits intra AVGaccuracy: 84.59 -> 90.89Improved
add FIA alignment (ablation)local baseline · Digits inter AVGaccuracy: 26.00 -> 30.16Improved
add FBM basis-matrix consistency on top of FIA (ablation)FIA · Digits inter AVGaccuracy: 30.16 -> 31.77Improved
add FBM on top of FIA (ablation)FIA · Digits intra AVGaccuracy: 90.89 -> 90.78No clear effect
add CND distillation (ablation)FIA+FBM · Digitsintra/inter accuracyMixed
add FRR feature relationship regularization (ablation)FIA+FBM · Digits interaccuracyImproved
add CND and FRR together (full FBCL) (ablation)FIA+FBM · Digitsintra AVG / inter AVG: 90.78 -> 93.10 intra; 31.77 -> 34.84 interImproved
FBCL vs FCCL+FCCL+ · Office-Caltech inter-domain AVGaccuracy: 26.00 -> 27.51Improved
FBCL vs FCCL on Office-Caltech intra AVGFCCL · Office-Caltech intra AVGaccuracy: 67.77 -> 67.98No clear effect
FBCL vs FedPSA under model homogeneityFedPSA · Office-Caltech inter AVG (ResNet-18)accuracy: 68.80 -> 68.99No clear effect
collaborative learning vs local baselinelocal baseline · Office-Caltech intra AVGaccuracy: 66.08 -> 62.64 (FedMD)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy