Decoupled Subgraph Federated Learning

• URL: http://arxiv.org/abs/2402.19163v2
• Date: Thu, 20 Jun 2024 08:18:17 GMT
• Title: Decoupled Subgraph Federated Learning
• Authors: Javad Aliakbari, Johan Östman, Alexandre Graell i Amat,
• Abstract summary: We address the challenge of federated learning on graph-structured data distributed across multiple clients. We present a novel framework for this scenario, named FedStruct, that harnesses deep structural dependencies. We validate the effectiveness of FedStruct through experimental results conducted on six datasets for semi-supervised node classification.
• Score: 57.588938805581044
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address the challenge of federated learning on graph-structured data distributed across multiple clients. Specifically, we focus on the prevalent scenario of interconnected subgraphs, where interconnections between different clients play a critical role. We present a novel framework for this scenario, named FedStruct, that harnesses deep structural dependencies. To uphold privacy, unlike existing methods, FedStruct eliminates the necessity of sharing or generating sensitive node features or embeddings among clients. Instead, it leverages explicit global graph structure information to capture inter-node dependencies. We validate the effectiveness of FedStruct through experimental results conducted on six datasets for semi-supervised node classification, showcasing performance close to the centralized approach across various scenarios, including different data partitioning methods, varying levels of label availability, and number of clients.

Related papers

• AdaRC: Mitigating Graph Structure Shifts during Test-Time [66.40525136929398]
  Test-time adaptation (TTA) has attracted attention due to its ability to adapt a pre-trained model to a target domain without re-accessing the source domain. We propose AdaRC, an innovative framework designed for effective and efficient adaptation to structure shifts in graphs.
  arXiv  Detail & Related papers  (2024-10-09T15:15:40Z)
• Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting [50.181824673039436]
  We propose a Graph Structure Self-Contrasting (GSSC) framework that learns graph structural information without message passing. The proposed framework is based purely on Multi-Layer Perceptrons (MLPs), where the structural information is only implicitly incorporated as prior knowledge. It first applies structural sparsification to remove potentially uninformative or noisy edges in the neighborhood, and then performs structural self-contrasting in the sparsified neighborhood to learn robust node representations.
  arXiv  Detail & Related papers  (2024-09-09T12:56:02Z)
• Boosting Graph Foundation Model from Structural Perspective [6.387816922598151]
  We boost graph foundation model from structural perspective and propose BooG. BooG constructs virtual super nodes to unify structural characteristics of graph data from different domains. We also propose a novel pre-training objective based on contrastive learning, which learns more expressive representations for graph data.
  arXiv  Detail & Related papers  (2024-07-29T12:22:16Z)
• Efficient Multi-View Graph Clustering with Local and Global Structure Preservation [59.49018175496533]
  We propose a novel anchor-based multi-view graph clustering framework termed Efficient Multi-View Graph Clustering with Local and Global Structure Preservation (EMVGC-LG) Specifically, EMVGC-LG jointly optimize anchor construction and graph learning to enhance the clustering quality. In addition, EMVGC-LG inherits the linear complexity of existing AMVGC methods respecting the sample number.
  arXiv  Detail & Related papers  (2023-08-31T12:12:30Z)
• Learning Representations without Compositional Assumptions [79.12273403390311]
  We propose a data-driven approach that learns feature set dependencies by representing feature sets as graph nodes and their relationships as learnable edges. We also introduce LEGATO, a novel hierarchical graph autoencoder that learns a smaller, latent graph to aggregate information from multiple views dynamically.
  arXiv  Detail & Related papers  (2023-05-31T10:36:10Z)
• Federated Learning on Non-IID Graphs via Structural Knowledge Sharing [47.140441784462794]
  federated graph learning (FGL) enables clients to train strong GNN models in a distributed manner without sharing their private data. We propose FedStar, an FGL framework that extracts and shares the common underlying structure information for inter-graph learning tasks. We perform extensive experiments over both cross-dataset and cross-domain non-IID FGL settings, demonstrating FedStar's superiority.
  arXiv  Detail & Related papers  (2022-11-23T15:12:16Z)
• Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs [7.4398547397969494]
  We propose a privacy-preserving framework to analyze the GW discrepancy of node embedding learned locally from graph neural networks. Our experiments show that, with strong privacy protections guaranteed by the $varilon$-LDP algorithm, the proposed framework not only preserves privacy in graph learning but also presents a noised structural metric under GW distance.
  arXiv  Detail & Related papers  (2022-02-01T23:32:33Z)
• Towards Federated Bayesian Network Structure Learning with Continuous Optimization [14.779035801521717]
  We present a cross-silo federated learning approach to estimate the structure of Bayesian network. We develop a distributed structure learning method based on continuous optimization.
  arXiv  Detail & Related papers  (2021-10-18T14:36:05Z)
• Secure Deep Graph Generation with Link Differential Privacy [32.671503863933616]
  We leverage the differential privacy (DP) framework to formulate and enforce rigorous privacy constraints on deep graph generation models. In particular, we enforce edge-DP by injecting proper noise to the gradients of a link reconstruction-based graph generation model. Our proposed DPGGAN model is able to generate graphs with effectively preserved global structure and rigorously protected individual link privacy.
  arXiv  Detail & Related papers  (2020-05-01T15:49:17Z)

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.