# Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning

arXiv: https://arxiv.org/abs/2508.05224 · HTML: https://mlsanity.com/paper/2508.05224/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Builds on (most cited first, 24 of 24)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [The Hidden Vulnerability of Distributed Learning in Byzantium](https://mlsanity.com/paper/1802.07927/) (2018)
- [FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients](https://mlsanity.com/paper/2207.09209/) (2022)
- [Measuring and regularizing networks in function space](https://mlsanity.com/paper/1805.08289/) (2018)
- [Learning to Detect Malicious Clients for Robust Federated Learning](https://mlsanity.com/paper/2002.00211/) (2020)
- [NVIDIA FLARE: Federated Learning from Simulation to Real-World](https://mlsanity.com/paper/2210.13291/) (2022)
- [Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging](https://mlsanity.com/paper/1909.05125/) (2019)
- [Federated Conformal Predictors for Distributed Uncertainty Quantification](https://mlsanity.com/paper/2305.17564/) (2023)
- [Byzantine-Robust Decentralized Learning via ClippedGossip](https://mlsanity.com/paper/2202.01545/) (2022)
- [Federated Learning for Privacy Preservation in Smart Healthcare Systems: A Comprehensive Survey](https://mlsanity.com/paper/2203.09702/) (2022)
- [Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering](https://mlsanity.com/paper/2109.05872/) (2021)
- [FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering](https://mlsanity.com/paper/2403.04144/) (2024)
- [Personalized Federated Learning with Attention-based Client Selection](https://mlsanity.com/paper/2312.15148/) (2023)
- [Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications](https://mlsanity.com/paper/2409.00974/) (2024)

## Built on by (most cited first, 3 of 3)

- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification](https://mlsanity.com/paper/2510.24749/) (2025)
- [State-of-the-art Small Language Coder Model: Mify-Coder](https://mlsanity.com/paper/2512.23747/) (2025)

## Abstract (arXiv)

Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy by keeping data local. Traditional FL approaches rely on a centralized, star-shaped topology, where a central server aggregates model updates from clients. However, this architecture introduces several limitations, including a single point of failure, limited personalization, and poor robustness to distribution shifts or vulnerability to malfunctioning clients. Moreover, update selection in centralized FL often relies on low-level parameter differences, which can be unreliable when client data is not independent and identically distributed, and offer clients little control. In this work, we propose a decentralized, peer-to-peer (P2P) FL framework. It leverages the flexibility of the P2P topology to enable each client to identify and aggregate a personalized set of trustworthy and beneficial updates.This framework is the Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR). Central to our method is an agreement score, computed on a local validation set, which quantifies the semantic alignment of incoming updates in the function space with respect to the clients reference model. Each client uses this score to select a tailored subset of updates and performs aggregation with a regularization term that further stabilizes the training. Our empirical evaluation across five datasets shows that the proposed approach consistently outperforms both, centralized baselines and existing P2P methods in terms of client-level performance, particularly under adversarial and heterogeneous conditions.