English

Prediction-space knowledge markets for communication-efficient federated learning on multimedia tasks

Machine Learning 2025-12-02 v1

Abstract

Federated learning (FL) enables collaborative training over distributed multimedia data but suffers acutely from statistical heterogeneity and communication constraints, especially when clients deploy large models. Classic parameter-averaging methods such as FedAvg transmit full model weights and can diverge under nonindependent and identically distributed (non-IID) data. We propose KTA v2, a prediction-space knowledge trading market for FL. Each round, clients locally train on their private data, then share only logits on a small public reference set. The server constructs a client-client similarity graph in prediction space, combines it with reference-set accuracy to form per-client teacher ensembles, and sends back personalized soft targets for a second-stage distillation update. This two-stage procedure can be interpreted as approximate block-coordinate descent on a unified objective with prediction-space regularization. Experiments on FEMNIST, CIFAR-10 and AG News show that, under comparable or much lower communication budgets, KTA v2 consistently outperforms a local-only baseline and strong parameter-based methods (FedAvg, FedProx), and substantially improves over a FedMD-style global teacher. On CIFAR-10 with ResNet-18, KTA v2 reaches 57.7% test accuracy using approximately 1/1100 of FedAvg's communication, while on AG News it attains 89.3% accuracy with approximately 1/300 of FedAvg's traffic.

Keywords

Cite

@article{arxiv.2512.00841,
  title  = {Prediction-space knowledge markets for communication-efficient federated learning on multimedia tasks},
  author = {Wenzhang Du},
  journal= {arXiv preprint arXiv:2512.00841},
  year   = {2025}
}

Comments

13 pages, 3 figures

R2 v1 2026-07-01T08:01:42.610Z