Skip to content
Book Open access

Correlation-Guided Latent Sharing for Non-IID Federated Learning

Nov 2026 · Proceedings of the 35th ACM International Conference on Information and Knowledge Management · pp. 7261-7265 · 0 citations · 17 references

TL;DR

Correlation-Guided Latent Sharing is proposed, a federated learning framework that selectively augments client training using latent information received from statistically aligned peers and improves accuracy and macro-F1 over FedAvg and FedProx, with the largest gains appearing in the strongest heterogeneity settings.

Abstract

Federated learning (FL) enables collaborative model training across distributed clients without centralizing raw data, but its performance often degrades under non-independent and non-identically distributed (non-IID) data. This degradation is especially severe when clients observe only a limited subset of the global label space, causing biased local updates and client drift. Standard aggregation methods such as FedAvg and FedProx mainly address this problem at the optimization level, but they do not directly enrich the incomplete local data distributions that cause heterogeneity. This paper proposes Correlation-Guided Latent Sharing (CGLS), a federated learning framework that selectively augments client training using latent information received from statistically aligned peers. CGLS identifies compatible clients through gradient-direction correlation and mixes local training data with synthetic latent information from correlated neighbors. We formulate this process as a mixed-distribution federated objective and explain how targeted mixing can reduce gradient dispersion under severe label skew. Experiments on MNIST, FashionMNIST and CIFAR-10 under Dirichlet and balanced one-class non-IID partitions show that CGLS improves accuracy and macro-F1 over FedAvg and FedProx, with the largest gains appearing in the strongest heterogeneity settings.

Read PDF

Similar papers

Joint Domain-Class Modeling for Federated Learning Under Feature Skew

The proposed Joint Domain-Class Federated Learning (JDFL), a lightweight, optimizer-agnostic extension that makes this latent domain variation usable without sharing raw data, and introduces two complementary supervision strategies based on simple intuitions.

Sina Najafi, Mostafa Tavassolipour, S. P. Shariatpanahi · 0 citations
Open access Sep 2026

Distribution-Aware Personalised Aggregation for Federated Deep Learning Under Non-IID Data

DAPA (Distribution-Aware Personalised Aggregation), a personalised federated deep learning framework that adaptively tailors the global aggregation to each client based on inter-client distribution similarity, is proposed and establishes a convergence bound showing that DAPA achieves a tighter error floor than uniform...

Qi-Yun Luo, Qi Tang · 1 citation
#machine learning Preprint Oct 2026

Latent Information Sharing for Accelerating Federated Learning

Federated learning (FL) is a communication-efficient distributed learning paradigm. However, client drift remains one of the most critical challenges, hindering the efficient training of a global model. In this study, we propose a novel latent information sharing scheme that directly mitigates data heterogeneity across...

Seung-Jun Lee, Ensieh Khazaei, Dimitrios Hatzinakos et al. · 1 citation
Book Open access Nov 2026

FedCSN: Mitigating Skewed Feature via Class-wise Selective Normalization in Federated Learning

Federated learning (FL) enables multiple distributed clients to collaboratively train a shared model without directly exchanging raw data. However, heterogeneous feature distributions across clients often lead to inconsistent local optimization and degraded model performance. Existing normalization-based augmentation m...

Hao-Jie Sun, Zhi-Hao Qu, Yan-Yan Wang et al. · 0 citations
Book Open access Nov 2026

FedGAT: Federated Geometry-Aware and Topological Condensation

Federated learning has emerged as a promising paradigm for privacy-preserving collaborative learning across distributed clients. However, the data owned by different clients are usually highly heterogeneous and severely Non-Independent and Identically Distributed (Non-IID), which leads to client drift and unsatisfactor...

Yuxuan Luan, Zi-Lin Zhao, Wei Wang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.