FedGL: Federated Graph Learning Framework with Global Self-Supervision

Chen, Chuan; Hu, Weibo; Xu, Ziyue; Zheng, Zibin

doi:10.48550/arxiv.2105.03170

Cited by 9 publications

(12 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The server in [Chen et al, 2021a] generates a global pseudo graph with node embeddings uploaded by FL clients, and distributes it to the clients to update their local graphs for GCN model training. Besides, the server also generates global pseudo node labels based on the uploaded node predictions, which are incorporated into the self-supervised learning loss of the clients to mitigate the non-IID data problem.…”

Section: Updating Clients' Local Graphsmentioning

confidence: 99%

Federated Graph Neural Networks: Overview, Techniques and Challenges

Li¹,

Han²

2022

Preprint

View full text Add to dashboard Cite

With its powerful capability to deal with graph data widely found in practical applications, graph neural networks (GNNs) have received significant research attention. However, as societies become increasingly concerned with data privacy, GNNs face the need to adapt to this new normal. This has led to the rapid development of federated graph neural networks (FedGNNs) research in recent years. Although promising, this interdisciplinary field is highly challenging for interested researchers to enter into. The lack of an insightful survey on this topic only exacerbates this problem. In this paper, we bridge this gap by offering a comprehensive survey of this emerging field. We propose a unique 3-tiered taxonomy of the FedGNNs literature to provide a clear view into how GNNs work in the context of Federated Learning (FL). It puts existing works into perspective by analyzing how graph data manifest themselves in FL settings, how GNN training is performed under different FL system architectures and degrees of graph data overlap across data silo, and how GNN aggregation is performed under various FL settings. Through discussions of the advantages and limitations of existing works, we envision future research directions that can help build more robust, dynamic, efficient, and interpretable FedGNNs.

show abstract

Section: Updating Clients' Local Graphsmentioning

confidence: 99%

Federated Graph Neural Networks: Overview, Techniques and Challenges

Li¹,

Han²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Hsieh et al [26] also propose an adversarial defense mechanism against attribute inference attacks on GNNs by maintaining the accuracy of target label classification and reducing the accuracy of private label classification. There is also increasing trend in using federated and split learning to address the privacy issues of GNNs in distributed learning settings [5,6,23,34,35,39,44,53,56,60,66,67]. However, none of the aforementioned works employ the notion of DP, and thus they do not provide provable privacy guarantees.…”

Section: Privacy-preserving Gnnsmentioning

confidence: 99%

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

Sajadmanesh¹,

Shamsabadi²,

Bellet³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) are powerful models designed for graph data that learn node representation by recursively aggregating information from each node's local neighborhood. However, despite their state-of-the-art performance in predictive graph-based applications, recent studies have shown that GNNs can raise significant privacy concerns when graph data contain sensitive information. As a result, in this paper, we study the problem of learning GNNs with Differential Privacy (DP). We propose GAP, a novel differentially private GNN that safeguards the privacy of nodes and edges using aggregation perturbation, i.e., adding calibrated stochastic noise to the output of the GNN's aggregation function, which statistically obfuscates the presence of a single edge (edge-level privacy) or a single node and all its adjacent edges (node-level privacy). To circumvent the accumulation of privacy cost at every forward pass of the model, we tailor the GNN architecture to the specifics of private learning. In particular, we first precompute private aggregations by recursively applying neighborhood aggregation and perturbing the output of each aggregation step. Then, we privately train a deep neural network on the resulting perturbed aggregations for any node-wise classification task. A major advantage of GAP over previous approaches is that we guarantee edgelevel and node-level DP not only for training, but also at inference time with no additional costs beyond the training's privacy budget. We theoretically analyze the formal privacy guarantees of GAP using Rényi DP. Empirical experiments conducted over three real-world graph datasets demonstrate that GAP achieves a favorable privacy-accuracy trade-off and significantly outperforms existing approaches.

show abstract

“…To solve this issue, numerous efforts have been made to build privacy-preserving graph learning (PPGL) [95,53,17,46,165] which aims to build graph learning framework while protecting users' data privacy. In this survey, we categorize previous research work of PPGL into three directions, namely, federated graph learning, privacy inference attack, and private graph learning.…”

Section: Overview and Taxonomymentioning

confidence: 99%

“…A typical example is user behavior modeling in online social platform, where each terminal user has a local social network and server wants to train a model to describe the user's behavior (e.g., fraud user detection and recommendation). In this case, horizontal intra-graph FL enables to train a powerful global model by leveraging information from all terminal users without violating their privacy [117,17,136]. Here, we introduce a prior work [126] focusing on federated recommendation modeling under this horizontal setting.…”

Section: Federated Graph Learningmentioning

confidence: 99%

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

Wu¹,

Li²,

Yu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite these progresses, how to ensure various deep graph learning algorithms behave in a socially responsible manner and meet regulatory compliance requirements becomes an emerging problem, especially in risk-sensitive domains. Trustworthy graph learning (TwGL) aims to solve the above problems from a technical viewpoint. In contrast to conventional graph learning research which mainly cares about model performance, TwGL considers various reliability and safety aspects of the graph

show abstract

FedGL: Federated Graph Learning Framework with Global Self-Supervision

Cited by 9 publications

References 47 publications

Federated Graph Neural Networks: Overview, Techniques and Challenges

Federated Graph Neural Networks: Overview, Techniques and Challenges

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

Contact Info

Product

Resources

About