Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning

Summary

arXiv:2607.01474v1 Announce Type: new Abstract: Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot be addressed by standard centralized techniques due to privacy and heterogeneity constraints. We propose FedCGNM (Federated Class-Grouped Normalized Momentum), a client-side optimizer in FL that partitions classes into a small number of groups based on minimum within-group variance, maintains a mom

SpinGraph analysis pending — check back after processing.

• How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size
• Token Geometry
• Geometry-Aware R-Structured Kolmogorov-Arnold Networks
• On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
• Conditional Inference Trees and Forests for Feature Selection
• The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning