Federated Social Recommendation with Graph Neural Network

Liu, Zhiwei; Yang, Liangwei; Fan, Ziwei; Peng, Hao; Yu, Philip S.

doi:10.1145/3501815

Cited by 74 publications

(25 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though on undirected graphs various such methods have been proposed and used for clustering [13, 24, 28, 29, 49, 59, 65ś 67, 72, 75, 84], particularly related to our work and model GRACE are the graph convolution based based models [28,29,84] which have been shown to achieve the state-of-the-art-results for Undi-AGC 6 . Recently, eforts have also been made to extend graph neural networks to other types of graphs such as directed graphs [35,43], hypergraphs [4,19,80], and more recently heteorgeneous graphs [18,22,23,36,41,57,70]. Amongst such extensions to heterogeneous graphs, we have GraphRec [18], KCGN [23], and FesoG [41].…”

Section: Methods That Combine Graph Structure and Node Atributesmentioning

confidence: 99%

“…Recently, eforts have also been made to extend graph neural networks to other types of graphs such as directed graphs [35,43], hypergraphs [4,19,80], and more recently heteorgeneous graphs [18,22,23,36,41,57,70]. Amongst such extensions to heterogeneous graphs, we have GraphRec [18], KCGN [23], and FesoG [41]. GraphRec [18] is an attention network proposed for social recommendation.…”

Section: Methods That Combine Graph Structure and Node Atributesmentioning

confidence: 99%

“…This is because it is not clear how we may incorporate GraphRec's message passing scheme in the analysis even if we follow a similar approach as we do in our paper. FeSoG [41] proposes to employ federated learning to address the privacy concerns in social recommendation based on the fact that most graph neural networks for this task require a centralized storage of the social links and item interactions of users. The attention based graph neural network proposed in FeSoG is similar to GraphRec (discussed above), since FesoG is an attention network with a similar procedure to learn the embedding (besides the federated learning it employs).…”

Section: Methods That Combine Graph Structure and Node Atributesmentioning

confidence: 99%

See 2 more Smart Citations

GRACE: A General Graph Convolution Framework for Attributed Graph Clustering

Kamhoua

Zhang

et al. 2023

ACM Trans. Knowl. Discov. Data

View full text Add to dashboard Cite

Attributed graph clustering (AGC) is an important problem in graph mining as more and more complex data in real-world have been represented in graphs with attributed nodes. While it is a common practice to leverage both attribute and structure information for improved clustering performance, most existing AGC algorithms consider only a specific type of relations, which hinders their applicability to integrate various complex relations into node attributes for AGC. In this paper, we propose GRACE, an extended graph convolution framework for AGC tasks. Our framework provides a general and interpretative solution for clustering many different types of attributed graphs, including undirected, directed, heterogeneous and hyper attributed graphs. By building suitable graph Laplacians for each of the aforementioned graph types, GRACE can seamlessly perform graph convolution on node attributes to fuse all available information for clustering. We conduct extensive experiments on 14 real-world datasets of 4 different graph types. The experimental results show that GRACE outperforms the state-of-the-art AGC methods on the different graph types in terms of clustering quality, time, and memory usage.

show abstract

Section: Methods That Combine Graph Structure and Node Atributesmentioning

confidence: 99%

Section: Methods That Combine Graph Structure and Node Atributesmentioning

confidence: 99%

Section: Methods That Combine Graph Structure and Node Atributesmentioning

confidence: 99%

See 1 more Smart Citation

GRACE: A General Graph Convolution Framework for Attributed Graph Clustering

Kamhoua

Zhang

et al. 2023

ACM Trans. Knowl. Discov. Data

View full text Add to dashboard Cite

show abstract

“…Feddy [191] Inter GC SpreadGNN [192] Inter GC GCFL [193] Inter GC FedCBT [194] Inter GC FedChem [195] Inter GC STFL [196] Inter GC FedGNN [197] Inter R FeSoG [198] Inter R…”

Section: Methods Category Taskmentioning

confidence: 99%

Trustworthy Graph Neural Networks: Aspects, Methods and Trends

Zhang¹,

Wu²,

Yuan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering to cutting-edge technologies such as drug discovery in life sciences and n-body simulation in astrophysics. However, task performance is not the only requirement for GNNs. Performance-oriented GNNs have exhibited potential adverse effects like vulnerability to adversarial attacks, unexplainable discrimination against disadvantaged groups, or excessive resource consumption in edge computing environments. To avoid these unintentional harms, it is necessary to build competent GNNs characterised by trustworthiness. To this end, we propose a comprehensive roadmap to build trustworthy GNNs from the view of the various computing technologies involved. In this survey, we introduce basic concepts and comprehensively summarise existing efforts for trustworthy GNNs from six aspects, including robustness, explainability, privacy, fairness, accountability, and environmental well-being. Additionally, we highlight the intricate cross-aspect relations between the above six aspects of trustworthy GNNs. Finally, we present a thorough overview of trending directions for facilitating the research and industrialisation of trustworthy GNNs.

show abstract

“…A naive method is to align the embeddings of overlapping users and items directly. However, the server can easily infer a user's user-item links by recording the items with non-zero-gradient embeddings from this user because an item embedding gets updated on the user only when the item has the rating score from the user [66].…”

Section: User-item Graph-based Alignmentmentioning

confidence: 99%

Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applications

Fu¹,

Zhang²,

Dong³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph machine learning has gained great attention in both academia and industry recently. Most of the graph machine learning models, such as Graph Neural Networks (GNNs), are trained over massive graph data. However, in many realworld scenarios, such as hospitalization prediction in healthcare systems, the graph data is usually stored at multiple data owners and cannot be directly accessed by any other parties due to privacy concerns and regulation restrictions. Federated Graph Machine Learning (FGML) is a promising solution to tackle this challenge by training graph machine learning models in a federated manner. In this survey, we conduct a comprehensive review of the literature in FGML. Specifically, we first provide a new taxonomy to divide the existing problems in FGML into two settings, namely, FL with structured data and structured FL. Then, we review the mainstream techniques in each setting and elaborate on how they address the challenges under FGML. In addition, we summarize the real-world applications of FGML from different domains and introduce open graph datasets and platforms adopted in FGML. Finally, we present several limitations in the existing studies with promising research directions in this field.

show abstract

Federated Social Recommendation with Graph Neural Network

Cited by 74 publications

References 67 publications

GRACE: A General Graph Convolution Framework for Attributed Graph Clustering

GRACE: A General Graph Convolution Framework for Attributed Graph Clustering

Trustworthy Graph Neural Networks: Aspects, Methods and Trends

Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applications

Contact Info

Product

Resources

About