# HeteRo-Select: Informativeness as the Participation Driver in Heterogeneous Federated Learning

Source: [HeteRo-Select: Informativeness as the Participation Driver in Heterogeneous Federated Learning](<https://www.sota2.com/research/paper/68fa7a7e1e209131cea8378a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-18T05:00:06.089Z

Authors: Md. Akmol Masud, Md Abrar Jahin, Mahmud Hasan

Published: 2025-08-08T20:33:34.000Z

## Abstract

Federated learning systems typically allocate gradient compression by link speed. This is sensible when bandwidth and data informativeness align. However, under non-IID data, these signals often decorrelate or invert. A bandwidth-driven allocator then risks compressing the most informative gradients hardest. We propose HeteRo-Select, a framework that replaces bandwidth with a per-client informativeness score as the primary driver of compression. The score jointly governs three decisions per round: client selection, compression ratio, and server aggregation weight, with bandwidth retained only as a hard ceiling. Score-proportional selection provably reduces the effective heterogeneity of the chosen subset; score-proportional compression provably lowers aggregate top-$k$ error at fixed traffic. Under the exact FedCG simulation protocol, HeteRo-Select delivers a $1.78\\times$ speedup and an $18.2\\%$ reduction in traffic on CIFAR-10. The same configuration, unchanged, scales from a $7{,}850$-parameter logistic regression to an $11.27$M-parameter ResNet-18, hitting the accuracy target on three of four benchmarks. When bandwidth and informativeness are deliberately anti-correlated, the method still achieves the target accuracy with less traffic than the normal-bandwidth run.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-10 (Efficiency Metrics: Time and Traffic)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-efficiency-metrics-time-and-traffic.md>): Image Classification; CIFAR-10; Inference Time (s): 2906.

- [Image Classification on CIFAR-100 (Time and Traffic)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-time-and-traffic.md>): Image Classification; CIFAR-100; Time (s): 4549.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.06692>)

[PDF](<https://arxiv.org/pdf/2508.06692.pdf>)