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

arXiv: https://arxiv.org/abs/2512.00841 · HTML: https://mlsanity.com/paper/2512.00841/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 30 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data](https://mlsanity.com/paper/2008.06180/) (2020)
- [FedFed: Feature Distillation against Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2310.05077/) (2023)
- [Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions](https://mlsanity.com/paper/2406.10861/) (2024)
- [Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design](https://mlsanity.com/paper/2110.13388/) (2021)

## Abstract (arXiv)

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.