# Sparse Incremental Aggregation in Multi-Hop Federated Learning

arXiv: https://arxiv.org/abs/2407.18200 · HTML: https://mlsanity.com/paper/2407.18200/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 25 Jul 2024.

## Builds on (most cited first, 8 of 8)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Sparse Communication for Distributed Gradient Descent](https://mlsanity.com/paper/1704.05021/) (2017)
- [The Convergence of Sparsified Gradient Methods](https://mlsanity.com/paper/1809.10505/) (2018)
- [Rethinking gradient sparsification as total error minimization](https://mlsanity.com/paper/2108.00951/) (2021)
- [Ground-Assisted Federated Learning in LEO Satellite Constellations](https://mlsanity.com/paper/2109.01348/) (2021)
- [Time-Correlated Sparsification for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2101.08837/) (2021)
- [On-Board Federated Learning for Dense LEO Constellations](https://mlsanity.com/paper/2111.12769/) (2021)
- [Federated Learning in Satellite Constellations](https://mlsanity.com/paper/2206.00307/) (2022)

## Abstract (arXiv)

This paper investigates federated learning (FL) in a multi-hop communication setup, such as in constellations with inter-satellite links. In this setup, part of the FL clients are responsible for forwarding other client's results to the parameter server. Instead of using conventional routing, the communication efficiency can be improved significantly by using in-network model aggregation at each intermediate hop, known as incremental aggregation (IA). Prior works [1] have indicated diminishing gains for IA under gradient sparsification. Here we study this issue and propose several novel correlated sparsification methods for IA. Numerical results show that, for some of these algorithms, the full potential of IA is still available under sparsification without impairing convergence. We demonstrate a 15x improvement in communication efficiency over conventional routing and a 11x improvement over state-of-the-art (SoA) sparse IA.