Data-Topology Compatibility Enables Personalization in Decentralized Learning

arXiv:2610.15126 · stat.ML, cs.LG · Submitted 2026-10-10 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-10-10

Updated: 2026-10-10

Code: https://github.com/Veronicaaa1/orbit-personalization

Terminology

• Decentralized Learning — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes

Sources

• Layer Normalization
• FedSPD: A Soft-clustering Approach for Personalized Decentralized Federated Learning
• Improved Convergence Analysis of Topology Dependence in Decentralized SGD

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier