Federated graph neural networks: overview, techniques, and challenges
Graph neural networks (GNNs) have attracted extensive research attention in recent years due to their capability to progress with graph data and have been widely used in practical applications. As societies become increasingly concerned with the need for data privacy protection, GNNs face the need t...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/179063 |
| _version_ | 1811690717110599680 |
|---|---|
| author | Liu, Rui Xing, Pengwei Deng, Zichao Li, Anran Guan, Cuntai Yu, Han |
| author2 | College of Computing and Data Science |
| author_facet | College of Computing and Data Science Liu, Rui Xing, Pengwei Deng, Zichao Li, Anran Guan, Cuntai Yu, Han |
| author_sort | Liu, Rui |
| collection | NTU |
| description | Graph neural networks (GNNs) have attracted extensive research attention in recent years due to their capability to progress with graph data and have been widely used in practical applications. As societies become increasingly concerned with the need for data privacy protection, GNNs face the need to adapt to this new normal. Besides, as clients in federated learning (FL) may have relationships, more powerful tools are required to utilize such implicit information to boost performance. This has led to the rapid development of the emerging research field of federated GNNs (FedGNNs). This promising interdisciplinary field is highly challenging for interested researchers to grasp. The lack of an insightful survey on this topic further exacerbates the entry difficulty. In this article, we bridge this gap by offering a comprehensive survey of this emerging field. We propose a 2-D taxonomy of the FedGNN literature: 1) the main taxonomy provides a clear perspective on the integration of GNNs and FL by analyzing how GNNs enhance FL training as well as how FL assists GNN training and 2) the auxiliary taxonomy provides a view on how FedGNNs deal with heterogeneity across FL clients. Through discussions of key ideas, challenges, and limitations of existing works, we envision future research directions that can help build more robust, explainable, efficient, fair, inductive, and comprehensive FedGNNs. |
| first_indexed | 2024-10-01T06:08:26Z |
| format | Journal Article |
| id | ntu-10356/179063 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:08:26Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1790632024-07-18T02:03:54Z Federated graph neural networks: overview, techniques, and challenges Liu, Rui Xing, Pengwei Deng, Zichao Li, Anran Guan, Cuntai Yu, Han College of Computing and Data Science School of Computer Science and Engineering Computer and Information Science Artificial intelligence Federated learning Graph neural networks (GNNs) have attracted extensive research attention in recent years due to their capability to progress with graph data and have been widely used in practical applications. As societies become increasingly concerned with the need for data privacy protection, GNNs face the need to adapt to this new normal. Besides, as clients in federated learning (FL) may have relationships, more powerful tools are required to utilize such implicit information to boost performance. This has led to the rapid development of the emerging research field of federated GNNs (FedGNNs). This promising interdisciplinary field is highly challenging for interested researchers to grasp. The lack of an insightful survey on this topic further exacerbates the entry difficulty. In this article, we bridge this gap by offering a comprehensive survey of this emerging field. We propose a 2-D taxonomy of the FedGNN literature: 1) the main taxonomy provides a clear perspective on the integration of GNNs and FL by analyzing how GNNs enhance FL training as well as how FL assists GNN training and 2) the auxiliary taxonomy provides a view on how FedGNNs deal with heterogeneity across FL clients. Through discussions of key ideas, challenges, and limitations of existing works, we envision future research directions that can help build more robust, explainable, efficient, fair, inductive, and comprehensive FedGNNs. Agency for Science, Technology and Research (A*STAR) AI Singapore Nanyang Technological University National Research Foundation (NRF) Published version This work was supported in part by the National Research Foundation, Singapore, and Defence Science Organisation (DSO) National Laboratories through the AI Singapore Programme under AISG Award AISG2-RP-2020-019; in part by the Alibaba Group through the Alibaba Innovative Research (AIR) Program and the Alibaba-NTU Singapore Joint Research Institute (JRI) (Alibaba-NTUAIR2019B1), Nanyang Technological University (NTU), Singapore; in part by the RIE 2020 Advanced Manufacturing and Engineering (AME) Programmatic Fund, Singapore, under Grant A20G8b0102; in part by the Nanyang Technological University through the Nanyang Assistant Professorship (NAP); and in part by the Future Communications Research and Development Programme under Grant FCP-NTU-RG-2021-014. 2024-07-18T02:03:54Z 2024-07-18T02:03:54Z 2024 Journal Article Liu, R., Xing, P., Deng, Z., Li, A., Guan, C. & Yu, H. (2024). Federated graph neural networks: overview, techniques, and challenges. IEEE Transactions On Neural Networks and Learning Systems. https://dx.doi.org/10.1109/TNNLS.2024.3360429 2162-237X https://hdl.handle.net/10356/179063 10.1109/TNNLS.2024.3360429 en AISG2-RP-2020-019 A20G8b0102 IEEE Transactions on Neural Networks and Learning Systems © 2024 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. application/pdf |
| spellingShingle | Computer and Information Science Artificial intelligence Federated learning Liu, Rui Xing, Pengwei Deng, Zichao Li, Anran Guan, Cuntai Yu, Han Federated graph neural networks: overview, techniques, and challenges |
| title | Federated graph neural networks: overview, techniques, and challenges |
| title_full | Federated graph neural networks: overview, techniques, and challenges |
| title_fullStr | Federated graph neural networks: overview, techniques, and challenges |
| title_full_unstemmed | Federated graph neural networks: overview, techniques, and challenges |
| title_short | Federated graph neural networks: overview, techniques, and challenges |
| title_sort | federated graph neural networks overview techniques and challenges |
| topic | Computer and Information Science Artificial intelligence Federated learning |
| url | https://hdl.handle.net/10356/179063 |
| work_keys_str_mv | AT liurui federatedgraphneuralnetworksoverviewtechniquesandchallenges AT xingpengwei federatedgraphneuralnetworksoverviewtechniquesandchallenges AT dengzichao federatedgraphneuralnetworksoverviewtechniquesandchallenges AT lianran federatedgraphneuralnetworksoverviewtechniquesandchallenges AT guancuntai federatedgraphneuralnetworksoverviewtechniquesandchallenges AT yuhan federatedgraphneuralnetworksoverviewtechniquesandchallenges |