Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client (2405.08183v2)

Published 13 May 2024 in cs.LG and cs.AI

Abstract: Although Federated Learning (FL) is promising in knowledge sharing for heterogeneous Artificial Intelligence of Thing (AIoT) devices, their training performance and energy efficacy are severely restricted in practical battery-driven scenarios due to the ``wooden barrel effect'' caused by the mismatch between homogeneous model paradigms and heterogeneous device capability. As a result, due to various kinds of differences among devices, it is hard for existing FL methods to conduct training effectively in energy-constrained scenarios, such as battery constraints of devices. To tackle the above issues, we propose an energy-aware FL framework named DR-FL, which considers the energy constraints in both clients and heterogeneous deep learning models to enable energy-efficient FL. Unlike Vanilla FL, DR-FL adopts our proposed Muti-Agents Reinforcement Learning (MARL)-based dual-selection method, which allows participated devices to make contributions to the global model effectively and adaptively based on their computing capabilities and energy capacities in a MARL-based manner. Experiments conducted with various widely recognized datasets demonstrate that DR-FL has the capability to optimize the exchange of knowledge among diverse models in large-scale AIoT systems while adhering to energy limitations. Additionally, it improves the performance of each individual heterogeneous device's model.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. Personalized Real-Time Federated Learning for Epileptic Seizure Detection. IEEE Journal of Biomedical and Health Informatics 26 (2021), 898–909. https://api.semanticscholar.org/CorpusID:235786959
  2. INVITED: New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design. Proceedings of 57th ACM/IEEE Design Automation Conference (DAC) (2020), 1–6. https://api.semanticscholar.org/CorpusID:221293302
  3. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In Proceedings of Conference on Empirical Methods in Natural Language Processing.
  4. HELCFL: High-Efficiency and Low-Cost Federated Learning in Heterogeneous Mobile-Edge Computing. 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE) (2022), 1227–1232. https://api.semanticscholar.org/CorpusID:248922002
  5. HeteroFL: Computation and communication efficient federated learning for heterogeneous clients. In Proceedings of International Conference on Learning Representations (ICLR).
  6. Federated Learning Over Energy Harvesting Wireless Networks. IEEE Internet of Things Journal 9, 1 (2022), 92–103.
  7. Deep Residual Learning for Image Recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770–778 pages.
  8. ScaleFL: Resource-Adaptive Federated Learning with Heterogeneous Clients. In Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  9. Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges. IEEE Communications Surveys & Tutorials 23 (2020), 1759–1799. https://api.semanticscholar.org/CorpusID:221970627
  10. Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. https://api.semanticscholar.org/CorpusID:18268744
  11. To Talk or to Work: Flexible Communication Compression for Energy Efficient Federated Learning over Heterogeneous Mobile Edge Devices. IEEE INFOCOM 2021 - IEEE Conference on Computer Communications, 1–10. https://api.semanticscholar.org/CorpusID:229349304
  12. SmartPC: Hierarchical Pace Control in Real-Time Federated Learning System. 2019 IEEE Real-Time Systems Symposium (RTSS) (2019), 406–418. https://api.semanticscholar.org/CorpusID:203582658
  13. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proceedings of International Conference on Artificial Intelligence and Statistics. https://api.semanticscholar.org/CorpusID:14955348
  14. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proceedings of International Conference on Artificial Intelligence and Statistics.
  15. Reading Digits in Natural Images with Unsupervised Feature Learning. https://api.semanticscholar.org/CorpusID:16852518
  16. Federated Learning for Internet of Things: A Comprehensive Survey. IEEE Communications Surveys & Tutorials 23 (2021), 1622–1658. https://api.semanticscholar.org/CorpusID:233289549
  17. QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. ArXiv abs/1803.11485 (2018). https://api.semanticscholar.org/CorpusID:4533648
  18. Automotive Cyber-Physical Systems: A Tutorial Introduction. https://api.semanticscholar.org/CorpusID:247235211
  19. Toward Energy-Efficient Federated Learning Over 5G+ Mobile Devices. IEEE Wireless Communications 29 (2021), 44–51. https://api.semanticscholar.org/CorpusID:231592874
  20. Energy-Aware Analog Aggregation for Federated Learning with Redundant Data. In ICC 2020 - 2020 IEEE International Conference on Communications (ICC). 1–7. https://api.semanticscholar.org/CorpusID:207869996
  21. BranchyNet: Fast inference via early exiting from deep neural networks. In Proceedings of 23rd International Conference on Pattern Recognition (ICPR). 2464–2469 pages.
  22. A Survey on Distributed Machine Learning. ACM Computing Surveys (CSUR) 53 (2019), 1–33. https://api.semanticscholar.org/CorpusID:209439571
  23. Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning. ArXiv abs/2202.07470 (2022). https://api.semanticscholar.org/CorpusID:245446614
  24. PervasiveFL: Pervasive Federated Learning forHeterogeneous IoT Systems. IEEE Transactions on Computer Aided Design of Integrated Circuits Systems 41, 11 (2022), 4100–4111.
  25. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. ArXiv:1708.07747 (2017).
  26. Energy Efficient Federated Learning Over Wireless Communication Networks. IEEE Transactions on Wireless Communications 20 (2019), 1935–1949. https://api.semanticscholar.org/CorpusID:207880723
  27. SlimFL: Federated Learning With Superposition Coding Over Slimmable Neural Networks. IEEE/ACM Transactions on Networking (TON) 31, 6 (2023), 2499–2514.
  28. Jing Zhang and Dacheng Tao. 2020. Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things. IEEE Internet of Things Journal 8 (2020), 7789–7817. https://api.semanticscholar.org/CorpusID:226975900
  29. Self-Distillation: Towards Efficient and Compact Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 8 (2021), 4388–4403. https://api.semanticscholar.org/CorpusID:232302458
  30. Efficient Federated Learning for Cloud-Based AIoT Applications. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 40, 11 (2021), 221–2223. https://doi.org/10.1109/TCAD.2020.3046665
  31. Data-Free Knowledge Distillation for Heterogeneous Federated Learning. Proceedings of machine learning research 139 (2021), 12878–12889. https://api.semanticscholar.org/CorpusID:235125689
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Jun Xia (76 papers)
  2. Yiyu Shi (136 papers)
  3. Yi Zhang (994 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets