mlsanityData to 7 Oct 2026

Federated Learning Optimization: A Comparative Study of Data and Model Exchange Strategies in Dynamic Networks

arXiv 2406.10798 ↗First posted 16 Jun 2024cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

The promise and proliferation of large-scale dynamic federated learning gives rise to a prominent open question - is it prudent to share data or model across nodes, if efficiency of transmission and fast knowledge transfer are the prime objectives. This work investigates exactly that. Specifically, we study the choices of exchanging raw data, synthetic data, or (partial) model updates among devices. The implications of these strategies in the context of foundational models are also examined in detail. Accordingly, we obtain key insights about optimal data and model exchange mechanisms considering various environments with different data distributions and dynamic device and network connections. Across various scenarios that we considered, time-limited knowledge transfer efficiency can differ by up to 9.08%, thus highlighting the importance of this work.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 25 references that are in the map. First posted on arXiv 16 Jun 2024.

Builds on

15 of 25 references.

References · 15

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017Neural Discrete Representation Learningcited by 4,650
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  6. 2019Advances and Open Problems in Federated Learningcited by 3,021
  7. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  8. 2019Towards Federated Learning at Scale: System Designcited by 826
  9. 2014One weird trick for parallelizing convolutional neural networkscited by 264
  10. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 258
  11. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  12. 2019Peer-to-peer Federated Learning on Graphscited by 85
3 more
  1. 2020Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applicationscited by 58
  2. 2020Federated Learning via Synthetic Datacited by 53
  3. 2022FedSynth: Gradient Compression via Synthetic Data in Federated Learningcited by 30

Built on by

Not cited yet.