Graph Learning Across Data Silos

• URL: http://arxiv.org/abs/2301.06662v3
• Date: Fri, 1 Mar 2024 06:32:40 GMT
• Title: Graph Learning Across Data Silos
• Authors: Xiang Zhang and Qiao Wang
• Abstract summary: We consider the problem of inferring graph topology from smooth graph signals in a novel but practical scenario. Data are located in distributed clients and prohibited from leaving local clients due to factors such as privacy concerns. We 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.
• Score: 12.343382413705394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Toward Personalized Federated Node Classification in One-shot Communication [27.325478113745206]
  We propose a one-shot personalized Federated Graph Learning method for node classification. Our method estimates and aggregates class-wise feature distribution statistics to construct a global pseudo-graph on the server. Our method significantly outperforms state-of-the-art baselines across various settings.
  arXiv  Detail & Related papers  (2024-11-18T05:59:29Z)
• Federated Graph Learning with Graphless Clients [52.5629887481768]
  Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs) We propose a novel framework FedGLS to tackle the problem in FGL with graphless clients.
  arXiv  Detail & Related papers  (2024-11-13T06:54:05Z)
• GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networks [69.97213941893351]
  The emergence of Graph Neural Networks (GNNs) in graph data analysis has raised critical concerns about data misuse during model training. Existing methodologies address either data misuse detection or mitigation, and are primarily designed for local GNN models. This paper introduces a pioneering approach called GraphGuard, to tackle these challenges.
  arXiv  Detail & Related papers  (2023-12-13T02:59:37Z)
• GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks [72.01829954658889]
  This paper introduces the mathematical definition of this novel problem setting. We devise a general framework that coordinates a single graph-shared structure learner and multiple graph-specific GNNs. The well-trained structure learner can directly produce adaptive structures for unseen target graphs without any fine-tuning.
  arXiv  Detail & Related papers  (2023-06-20T03:33:22Z)
• Generated Graph Detection [27.591612297045817]
  Graph generative models become increasingly effective for data distribution approximation and data augmentation. We propose the first framework to investigate a set of sophisticated models and their performance in four classification scenarios. Our solution can sustain for a decent while to curb generated graph misuses.
  arXiv  Detail & Related papers  (2023-06-13T13:18:04Z)
• FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs [22.649780281947837]
  In some practical scenarios, graph data are stored separately in multiple distributed parties, which may not be directly shared due to conflicts of interest. We propose FedEgo, a federated graph learning framework based on ego-graphs to tackle the challenges above.
  arXiv  Detail & Related papers  (2022-08-29T15:47:36Z)
• A Graph-Enhanced Click Model for Web Search [67.27218481132185]
  We propose a novel graph-enhanced click model (GraphCM) for web search. We exploit both intra-session and inter-session information for the sparsity and cold-start problems.
  arXiv  Detail & Related papers  (2022-06-17T08:32:43Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• Distributed Graph Learning with Smooth Data Priors [61.405131495287755]
  We propose a novel distributed graph learning algorithm, which permits to infer a graph from signal observations on the nodes. Our results show that the distributed approach has a lower communication cost than a centralised algorithm without compromising the accuracy in the inferred graph.
  arXiv  Detail & Related papers  (2021-12-11T00:52:02Z)
• FedGL: Federated Graph Learning Framework with Global Self-Supervision [22.124339267195822]
  FedGL is capable of obtaining a high-quality global graph model while protecting data privacy. The global self-supervision enables the information of each client to flow and share in a privacy-preserving manner.
  arXiv  Detail & Related papers  (2021-05-07T11:27:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.