mlsanityData to 14 Oct 2026

Beyond Weights and Gradients: A Taxonomy of Federated Learning Messages

arXiv 2606.16891 ↗First posted 15 Jun 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning is rapidly evolving beyond the exchange of traditional model weights and gradients, yet existing definitions fail to capture the full scope of modern payloads like synthetic data and federated analytics. This paper addresses the gap by proposing a formal mathematical definition of a federated message that accounts for both utility and privacy. We introduce a taxonomy that organizes these exchanges into three categories: model structures, statistical summaries, and data-conditioned representations. By evaluating these groups based on computational demands, communication costs, and privacy risks, we provide a clearer understanding of the trade-offs involved in decentralized training. Our review of 202 recent publications highlights a significant shift since 2021 toward diverse messaging paradigms, signaling a move away from standard deep learning updates toward more specialized information sharing. This framework provides a structured path for future research to optimize federated systems for varying hardware and security requirements.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

26 of 36 references.

References · 26

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  5. 2019Deep Leakage from Gradientscited by 1,021
  6. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  8. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  9. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  10. 2019Practical Federated Gradient Boosting Decision Treescited by 54
  11. 2020Federated Learning via Synthetic Datacited by 54
  12. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 41
14 more
  1. 2021Emerging Trends in Federated Learning: From Model Fusion to Federated X Learningcited by 35
  2. 2021Towards Federated Bayesian Network Structure Learning with Continuous Optimizationcited by 31
  3. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  4. 2024A Survey on Efficient Federated Learning Methods for Foundation Model Trainingcited by 29
  5. 2022Towards Efficient Communications in Federated Learning: A Contemporary Surveycited by 24
  6. 2021FedDAG: Federated DAG Structure Learningcited by 17
  7. 2023Federated Learning without Full Labels: A Surveycited by 13
  8. 2024Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutionscited by 9
  9. 2022FedSyn: Synthetic Data Generation using Federated Learningcited by 7
  10. 2023Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learningcited by 7
  11. 2024Federated Knowledge Recycling: Privacy-Preserving Synthetic Data Sharingcited by 7
  12. 2024A Survey on Federated Analytics: Taxonomy, Enabling Techniques, Applications and Open Issuescited by 3
  13. 2026The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statisticscited by 3
  14. 2025Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insightscited by 1

Built on by

Not cited yet.