# Momentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligence

arXiv: https://arxiv.org/abs/2609.31159 · HTML: https://mlsanity.com/paper/2609.31159/

## 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 (most cited first, 8 of 8)

- [Distributed learning of deep neural network over multiple agents](https://mlsanity.com/paper/1810.06060/) (2018)
- [Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks](https://mlsanity.com/paper/2303.15991/) (2023)
- [Momentum Benefits Non-IID Federated Learning Simply and Provably](https://mlsanity.com/paper/2306.16504/) (2023)
- [Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies](https://mlsanity.com/paper/2503.02891/) (2025)
- [Communication-Efficient Split Learning via Adaptive Feature-Wise Compression](https://mlsanity.com/paper/2307.10805/) (2023)
- [StoCFL: A Stochastically Clustered Federated Learning Framework for Non-IID Data with Dynamic Client Participation](https://mlsanity.com/paper/2303.00897/) (2023)
- [Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things](https://mlsanity.com/paper/2311.04944/) (2023)
- [Federated Split Learning with Improved Communication and Storage Efficiency](https://mlsanity.com/paper/2507.15816/) (2025)

## 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.