Connectivity-Aware Client Selection in Decentralized Federated Learning
cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
License: http://creativecommons.org/licenses/by/4.0/
The gist: Decentralized federated learning (DFL) has emerged as a scalable alternative to centralized federated learning, removing the single point of failure and communication bottleneck at the server.
Terminology
Abstract
Decentralized federated learning (DFL) has emerged as a scalable alternative to centralized federated learning, removing the single point of failure and communication bottleneck at the server. However, most existing decentralized approaches rely on full-neighborhood broadcasting, where each client transmits its model update to all of its neighbors in each communication round. While effective, this results in significant communication overhead and high energy consumption. This paper applies spectral graph tools as lightweight client selection methods that leverage the graph topology by analyzing the spectral properties of the graph Laplacian over a fixed communication graph. Specifically, we exploit eigenvector embeddings and heat/diffusion kernel similarities to guide each client in selecting only a subset of structurally relevant neighbors, i.e., those that are most beneficial for the convergence of the federation process. This topology aware randomization matches or outperforms uniform neighborhood subsampling and approaches the accuracy of full broadcasting. The largest gains, about 3 percentage points, emerge under strong data heterogeneity on larger, structurally rich graphs, while the total number of transmitted messages is reduced by 50% compared to naive broadcasting.
Sources
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- On-Device Federated Continual Learning on RISC-V-based Ultra-Low-Power SoC for Intelligent Nano-Drone Swarms
- Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense
- Fault-Tolerant Decentralized Distributed Asynchronous Federated Learning with Adaptive Termination Detection
- Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent
- Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
- Smart Sampling: Helping from Friendly Neighbors for Decentralized Federated Learning
- DELTA: Diverse Client Sampling for Fasting Federated Learning
- Fast Heterogeneous Federated Learning with Hybrid Client Selection
- node2vec: Scalable Feature Learning for Networks
- Lecture Notes on Spectral Graph Methods
- Rethinking Graph Transformers with Spectral Attention
- Swarm Learning: A Survey of Concepts, Applications, and Trends
- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents