Lumos: Heterogeneity-aware Federated Graph Learning over Decentralized Devices

2023-03-01 · Qiying Pan, Yifei Zhu, Lingyang Chu

Graph neural networks (GNN) have been widely deployed in real-world networked applications and systems due to their capability to handle graph-structured data. However, the growing awareness of data privacy severely challenges the traditional centralized model training paradigm, where a server holds all the graph information. Federated learning is an emerging collaborative computing paradigm that allows model training without data centralization. Existing federated GNN studies mainly focus on systems where clients hold distinctive graphs or sub-graphs. The practical node-level federated situation, where each client is only aware of its direct neighbors, has yet to be studied. In this paper, we propose the first federated GNN framework called Lumos that supports supervised and unsupervised learning with feature and degree protection on node-level federated graphs. We first design a tree constructor to improve the representation capability given the limited structural information. We further present a Monte Carlo Markov Chain-based algorithm to mitigate the workload imbalance caused by degree heterogeneity with theoretically-guaranteed performance. Based on the constructed tree for each client, a decentralized tree-based GNN trainer is proposed to support versatile training. Extensive experiments demonstrate that Lumos outperforms the baseline with significantly higher accuracy and greatly reduced communication cost and training time.

📄 PDF Abstract BibTeX arXiv:2303.00492

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning Graph Learning

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Lumos: Let there be Language Model System Certification

2025-12-02 · Isha Chaudhary, Vedaant Jain, Prineet Parhar, Kavya Sachdeva 외 arxiv

We introduce the first principled framework, Lumos, for specifying and formally certifying Language Model System (LMS) behaviors. Lumos is an imperative probabilistic programming DSL over graphs, with constructs to gener…

Autonomous Driving

Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity

2026-08-01 · Yinlin Zhu, Di Wu, Yi Zhang, Xunkai Li 외 arxiv

Multimodal-attributed graphs (MAGs), where nodes carry heterogeneous semantic content across multiple modalities while edges encode relational dependencies, have been widely adopted across diverse domains. Federated mult…

Contrastive Learning Graph Learning

Empowering Contrastive Federated Sequential Recommendation with LLMs

2026-02-10 · Thi Minh Chau Nguyen, Minh Hieu Nguyen, Duc Anh Nguyen, Xuan Huong Tran 외 arxiv

Federated sequential recommendation (FedSeqRec) aims to perform next-item prediction while keeping user data decentralised, yet model quality is frequently constrained by fragmented, noisy, and homogeneous interaction lo…

Sequential Recommendation Representation Learning Data Augmentation

Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach

2024-02-19 · Chengyi Ju, Jiannong Cao, Yu Yang, Zhen-Qun Yang 외

In the era of modern education, addressing cross-school learner diversity is crucial, especially in personalized recommender systems for elective course selection. However, privacy concerns often limit cross-school data …

Diversity Recommendation Systems

Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning

2026-01-29 · Wentao Yu, Sheng Wan, Shuo Chen, Bo Han 외 arxiv

Graph Federated Learning (GFL) enables distributed graph representation learning while protecting the privacy of graph data. However, GFL suffers from heterogeneity arising from diverse node features and structural topol…

Graph Representation Learning Federated Learning