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
- 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) - Efficient Distribution Similarity Identification in Clustered Federated
Learning via Principal Angles Between Client Data Subspaces [59.33965805898736]
Clustered learning has been shown to produce promising results by grouping clients into clusters.
Existing FL algorithms are essentially trying to group clients together with similar distributions.
Prior FL algorithms attempt similarities indirectly during training.
arXiv Detail & Related papers (2022-09-21T17:37:54Z) - 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) - Exploiting Shared Representations for Personalized Federated Learning [54.65133770989836]
We propose a novel federated learning framework and algorithm for learning a shared data representation across clients and unique local heads for each client.
Our algorithm harnesses the distributed computational power across clients to perform many local-updates with respect to the low-dimensional local parameters for every update of the representation.
This result is of interest beyond federated learning to a broad class of problems in which we aim to learn a shared low-dimensional representation among data distributions.
arXiv Detail & Related papers (2021-02-14T05:36:25Z) - Heterogeneous Federated Learning [41.04946606973614]
Federated learning learns from scattered data by fusing collaborative models from local nodes.
Due to chaotic information distribution, the model fusion may suffer from structural misalignment with regard to unmatched parameters.
We propose a novel federated learning framework to establish a firm structure-information alignment across collaborative models.
arXiv Detail & Related papers (2020-08-15T19:06:59Z) - 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.