mlsanityData to 7 Oct 2026

FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes

arXiv 2510.10380 ↗First posted 12 Oct 2025cs.DC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-Model Federated Learning (MMFL) is an emerging direction in Federated Learning (FL) where multiple models are trained in parallel, generally on various datasets. Optimizing the models' accuracies and training times in the MMFL setting requires adapting to data and system heterogeneity across clients as in single-model FL; these challenges are amplified in the MMFL setting due to additional heterogeneity across models. Neither existing solutions nor na"ive extensions of single-model FL frameworks efficiently address these challenges. To bridge this gap, we propose FLAMMABLE, a comprehensive MMFL training framework. FLAMMABLE optimizes model training by intelligently adapting client batch sizes while engaging them to train multiple carefully chosen models, depending on their system capabilities, in each training round. To evaluate FLAMMABLE, we develop the first benchmark platform for the MMFL setting, which may enable future reproducible MMFL research. Extensive evaluations on multiple datasets and models show that FLAMMABLE boosts the MMFL time-to-accuracy performance by 1.1~10.0× while improving the final model accuracy by 1.3~5.4% compared to several known baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 51 references that are in the map. First posted on arXiv 12 Oct 2025.

Builds on

22 of 51 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  4. 2018Federated Learning with Non-IID Datacited by 1,099
  5. 2020Adaptive Federated Optimizationcited by 1,036
  6. 2017Federated Multi-Task Learningcited by 669
  7. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  8. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  9. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  10. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  11. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
  12. 2018An Empirical Model of Large-Batch Trainingcited by 268
10 more
  1. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  2. 2017Revisiting Distributed Synchronous SGDcited by 142
  3. 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 76
  4. 2020Towards Flexible Device Participation in Federated Learningcited by 64
  5. 2020Mitigating Bias in Federated Learningcited by 56
  6. 2021FedLab: A Flexible Federated Learning Frameworkcited by 54
  7. 2019Benchmarking TPU, GPU, and CPU Platforms for Deep Learningcited by 51
  8. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  9. 2021Efficient Device Scheduling with Multi-Job Federated Learningcited by 29
  10. 2024FedTrans: Efficient Federated Learning via Multi-Model Transformationcited by 1

Built on by

Not cited yet.