Momentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligence
Not on the map. Why?
Abstract (arXiv)
We propose a momentum-guided federated split distillation framework for personalized, efficient, and autonomous temporal edge intelligence. We introduce TeRR-SAtt, our novel temporal reservoir student attention design that combines fixed reservoir representations, a lightweight temporal student, and personalized output modules. We also present AMGF, our anticipatory momentum-guided fusion mechanism that clusters clients through learning momentum and derives specialized teacher updates. On real-world smart-building data, TeRR-SAtt reduces edge training latency by 65.50%, inference latency by 44.70%, training memory usage by 18.40%, and inference CPU usage by 33.10% over the considered baselines. At the same time, AMGF improves local learning by up to 35.31% in RMSE compared to global updates.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 40 references that are in the map. First posted on arXiv 25 Sep 2026.
Builds on
8 of 40 references.
References · 8
- 2018Distributed learning of deep neural network over multiple agentscited by 279
- 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
- 2023Momentum Benefits Non-IID Federated Learning Simply and Provablycited by 38
- 2025Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategiescited by 24
- 2023Communication-Efficient Split Learning via Adaptive Feature-Wise Compressioncited by 18
- 2023StoCFL: A Stochastically Clustered Federated Learning Framework for Non-IID Data with Dynamic Client Participationcited by 4
- 2023Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Thingscited by 3
- 2025Federated Split Learning with Improved Communication and Storage Efficiencycited by 3
Built on by
Not cited yet.