Graph Learning Across Data Silos
Not on the map. Why?
Abstract (arXiv)
We consider the problem of inferring graph topology from smooth graph signals in a novel but practical scenario where data are located in distributed clients and prohibited from leaving local clients due to factors such as privacy concerns. The main difficulty in this task is how to exploit the potentially heterogeneous data of all clients under data silos. To this end, we first propose an auto-weighted multiple graph learning model to jointly learn a personalized graph for each local client and a single consensus graph for all clients. The personalized graphs match local data distributions, thereby mitigating data heterogeneity, while the consensus graph captures the global information. Moreover, the model can automatically assign appropriate contribution weights to local graphs based on their similarity to the consensus graph. We next devise a tailored algorithm to solve the induced problem, where all raw data are processed locally without leaving clients. Theoretically, we establish a provable estimation error bound and convergence analysis for the proposed model and algorithm. Finally, extensive experiments on synthetic and real data are carried out, and the results illustrate that our approach can learn graphs effectively in the target scenario.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 56 references that are in the map. First posted on arXiv 17 Jan 2023.
Builds on
29 of 56 references.
References · 29
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2017Federated Multi-Task Learningcited by 672
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2020The Future of Digital Health with Federated Learningcited by 633
- 2020Personalized Federated Learning with Moreau Envelopescited by 618
- 2021Towards Personalized Federated Learningcited by 464
17 more
- 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 413
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
- 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
- 2016How to learn a graph from smooth signalscited by 146
- 2018Adaptive Online Learning in Dynamic Environmentscited by 133
- 2018Learning graphs from data: A signal representation perspectivecited by 119
- 2018Connecting the Dots: Identifying Network Structure via Graph Signal Processingcited by 111
- 2017Personalized and Private Peer-to-Peer Machine Learningcited by 54
- 2019A Unified Framework for Structured Graph Learning via Spectral Constraintscited by 53
- 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
- 2022Personalized Federated Learning With Graphcited by 29
- 2021Learning to Learn Graph Topologiescited by 26
- 2021Online Discriminative Graph Learning from Multi-Class Smooth Signalscited by 13
- 2020Federated Block Coordinate Descent Scheme for Learning Global and Personalized Modelscited by 11
- 2021Fast Projected Newton-like Method for Precision Matrix Estimation under Total Positivitycited by 8
- 2021Joint Network Topology Inference via Structured Fusion Regularizationcited by 1
- 2021Time-varying Graph Learning Under Structured Temporal Priorscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.