๐ฎ
๐ฎ
The Ethereal
Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
July 01, 2026 ยท Grace Period ยท ๐ Proceedings of the 43 rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026
Authors
Haemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li, Balakrishnan Ananthanarayanan
arXiv ID
2607.01474
Category
cs.LG: Machine Learning
Citations
0
Venue
Proceedings of the 43 rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026
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 momentum per group, normalizes each group momentum to unit length, and uses the summation of the normalized group momentums as an update direction. This design both equalizes gradient magnitude across majority and minority groups and mitigates the noise inherent in rare-class gradients. We further provide a theoretical convergence analysis explicitly accounting for time-varying resampling-rates. Additionally, to efficiently optimize these rates in small-client regimes, we introduce FedHOO, an X-armed-bandit (XAB) based algorithm that exploits federated parallelism that evaluates many combinations of two candidate rates per client at linear cost. Empirical evaluation on four public long-tailed benchmarks and a proprietary chip-defect dataset demonstrates that FedCGNM consistently outperforms baselines, with FedHOO yielding further gains in small-scale federations.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Machine Learning
๐ฎ
๐ฎ
The Ethereal
Continuous control with deep reinforcement learning
๐
๐
Old Age
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
๐
๐
Old Age
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
๐
๐
Old Age
SGDR: Stochastic Gradient Descent with Warm Restarts
๐ฎ
๐ฎ
The Ethereal