{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T22:11:11Z","timestamp":1783462271519,"version":"3.55.0"},"reference-count":69,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T00:00:00Z","timestamp":1711411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGKDD Explor. Newsl."],"published-print":{"date-parts":[[2024,3,26]]},"abstract":"<jats:p>In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protecting sensitive attributes (e.g., age and gender), the fairness incurred by the graph structure should also be given attention. On the other hand, the information aggregation mechanism of graph neural networks amplifies such structure unfairness, as marginal nodes are often far away from other nodes. In this paper, we focus on novel fairness incurred by the graph structure on graph neural networks, named structure fairness. Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks. Motivated by the observation, we propose Structural Fair Graph Neural Network (SFairGNN), which combines neighborhood expansion based structure debiasing with hop-aware attentive information aggregation to achieve structure fairness. Our experiments show SFairGNN can significantly improve structure fairness while maintaining overall performance in the downstream tasks.<\/jats:p>","DOI":"10.1145\/3655103.3655105","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T10:10:58Z","timestamp":1711620658000},"page":"4-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Marginal Nodes Matter: Towards Structure Fairness in Graphs"],"prefix":"10.1145","volume":"25","author":[{"given":"Xiaotian","family":"Han","sequence":"first","affiliation":[{"name":"Texas A&amp;M University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixiong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting-Hsiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Texas A&amp;M University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jundong","family":"Li","sequence":"additional","affiliation":[{"name":"University of Virginia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Weill Cornell Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zou","sequence":"additional","affiliation":[{"name":"Texas A&amp;M University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,3,28]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"P. Adam G. Sam C. Soumith C. Gregory Y. Edward D. Zachary L. Zeming D. Alban A. Luca and L. Adam. Automatic differentiation in pytorch. In NeurIPS ."},{"key":"e_1_2_1_2_1","unstructured":"M. A. Ahmad A. Patel C. Eckert V. Kumar and A. Teredesai. Fairness in machine learning for healthcare. In KDD"},{"key":"e_1_2_1_3_1","author":"Alder G. S.","unstructured":"G. S. Alder and J. Gilbert. Achieving ethics and fairness in hiring: Going beyond the law. Journal of Business Ethics, \u00ac.","journal-title":"Journal of Business Ethics, \u00ac."},{"key":"e_1_2_1_4_1","volume-title":"Noise reduction in speech processing","author":"Benesty J.","unstructured":"J. Benesty, J. Chen, Y. Huang, and I. Cohen. Pearson correlation coefficient. In Noise reduction in speech processing, pages -- . Springer, ."},{"key":"e_1_2_1_5_1","unstructured":"M. Bogen and A. Rieke. Help wanted: An examination of hiring algorithms equity and bias ."},{"key":"e_1_2_1_6_1","unstructured":"P. Bonacich. Some unique properties of eigenvector centrality. Social networks \u00ac( ): -- ."},{"key":"e_1_2_1_7_1","unstructured":"S. P. Borgatti. Centrality and network flow. Social networks ( ): -- ."},{"key":"e_1_2_1_8_1","unstructured":"J. Bruna W. Zaremba A. Szlam and Y. LeCun. Spectral networks and locally connected networks on graphs. In ICLR ."},{"key":"e_1_2_1_9_1","unstructured":"S. Caton and C. Haas. Fairness in machine learning: A survey. arXiv preprint arXiv:\u00ac . ."},{"key":"e_1_2_1_10_1","unstructured":"X. Chen M. Hou T. Tang A. Kaur and F. Xia. Digital twin mobility profiling: A spatio-temporal graph learning approach. In \u00ac \u00ac IEEE \u00ac rd Int Conf on High Performance Computing & Communications pages -- ."},{"key":"e_1_2_1_11_1","volume-title":"ICDE","author":"Chen Z.","unstructured":"Z. Chen, T. Xiao, and K. Kuang. Ba-gnn: On learning bias-aware graph neural network. In ICDE, pages -- . IEEE, ."},{"key":"e_1_2_1_12_1","unstructured":"M. Choudhary C. Laclau and C. Largeron. A survey on fairness for machine learning on graphs. arXiv preprint arXiv:\u00ac\u00ac . ."},{"key":"e_1_2_1_13_1","unstructured":"E. Dai and S. Wang. Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. In WSDM ."},{"key":"e_1_2_1_14_1","unstructured":"E. Dai T. Zhao H. Zhu J. Xu Z. Guo H. Liu J. Tang and S. Wang. A comprehensive survey on trustworthy graph neural networks: Privacy robustness fairness and explainability. arXiv preprint arXiv:\u00ac\u00ac . ."},{"key":"e_1_2_1_15_1","unstructured":"M. Defferrard X. Bresson and P. Vandergheynst. Convolutional neural networks on graphs with fast localized spectral filtering. In NeurIPS ."},{"key":"e_1_2_1_16_1","volume-title":"International World Wide Web Conference","author":"Dong J.","unstructured":"J. Dong, Q. Zhang, X. Huang, K. Duan, Q. Tan, and Z. Jiang. Hierarchy-aware multi-hop question answering over knowledge graphs. In International World Wide Web Conference, pages \u00ac-- , ."},{"key":"e_1_2_1_17_1","volume-title":"ACM International Conference on Web Search and Data Mining","author":"Dong J.","unstructured":"J. Dong, Q. Zhang, X. Huang, Q. Tan, D. Zha, and Z. Zihao. Active ensemble learning for knowledge graph error detection. In ACM International Conference on Web Search and Data Mining, pages -- , ."},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the ACM Web Conference \u00ac \u00ac\u00ac","author":"Dong Y.","unstructured":"Y. Dong, N. Liu, B. Jalaian, and J. Li. Edits: Modeling and mitigating data bias for graph neural networks. In Proceedings of the ACM Web Conference \u00ac \u00ac\u00ac, pages \u00ac-- \u00ac, ."},{"key":"e_1_2_1_19_1","unstructured":"Y. Dong J. Ma C. Chen and J. Li. Fairness in graph mining: A survey. arXiv preprint arXiv:\u00ac\u00ac . ."},{"key":"e_1_2_1_20_1","unstructured":"X. Du Y. Pei W. Duivesteijn and M. Pechenizkiy. Fairness in network representation by latent structural heterogeneity in observational data. In AAAI ."},{"key":"e_1_2_1_21_1","volume-title":"Proceedings of the rd innovations in theoretical computer science conference","author":"Dwork C.","unstructured":"C. Dwork, M. Hardt, T. Pitassi, O. Reingold, and R. Zemel. Fairness through awareness. In Proceedings of the rd innovations in theoretical computer science conference, pages -- , ."},{"key":"e_1_2_1_22_1","unstructured":"W. Fan Y. Ma Q. Li Y. He E. Zhao J. Tang and D. Yin. Graph neural networks for social recommendation. In The world wide web conference \u00ac."},{"key":"e_1_2_1_23_1","unstructured":"M. Fey and J. E. Lenssen. Fast graph representation learning with pytorch geometric. arXiv preprint arXiv: . \u00ac \u00ac \u00ac."},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics, .","author":"Glorot X.","unstructured":"X. Glorot and Y. Bengio. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics, ."},{"key":"e_1_2_1_25_1","unstructured":"[26]W. Hamilton Z. Ying and J. Leskovec. Inductive representation learning on large graphs. In NeurIPS ."},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the ACM Web Conference \u00ac \u00ac\u00ac","author":"Han X.","unstructured":"X. Han, Z. Jiang, N. Liu, Q. Song, J. Li, and X. Hu. Geometric graph representation learning via maximizing rate reduction. In Proceedings of the ACM Web Conference \u00ac \u00ac\u00ac, pages -- , ."},{"key":"e_1_2_1_27_1","unstructured":"X. Huang Q. Song Y. Li and X. Hu. Graph recurrent networks with attributed random walks. In KDD \u00ac."},{"key":"e_1_2_1_28_1","unstructured":"Z. Jiang X. Han C. Fan Z. Liu X. Huang N. Zou A. Mostafavi and X. Hu. Topology matters in fair graph learning: a theoretical pilot study. ."},{"key":"e_1_2_1_29_1","unstructured":"Z. Jiang X. Han C. Fan Z. Liu N. Zou A. Mostafavi and X. Hu. Fmp: Toward fair graph message passing against topology bias. arXiv preprint arXiv:\u00ac\u00ac \u00ac. ."},{"key":"e_1_2_1_30_1","unstructured":"T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv: . \u00ac ."},{"key":"e_1_2_1_31_1","volume-title":"Network analysis","author":"Kosch\u00fctzki D.","unstructured":"D. Kosch\u00fctzki, K. A. Lehmann, L. Peeters, S. Richter, D. Tenfelde-Podehl, and O. Zlotowski. Centrality indices. In Network analysis, pages -- . Springer, ."},{"key":"e_1_2_1_32_1","unstructured":"O. D. Kose and Y. Shen. Fair node representation learning via adaptive data augmentation. arXiv preprint arXiv:\u00ac\u00ac . ."},{"key":"e_1_2_1_33_1","volume-title":"International Conference on Learning Representations, .","author":"Li P.","unstructured":"P. Li, Y. Wang, H. Zhao, P. Hong, and H. Liu. On dyadic fairness: Exploring and mitigating bias in graph connections. In International Conference on Learning Representations, ."},{"key":"e_1_2_1_34_1","unstructured":"H. Ling Z. Jiang M. Liu S. Ji and N. Zou. Graph mixup with soft alignments. arXiv preprint arXiv:- . ."},{"key":"e_1_2_1_35_1","unstructured":"Z. Liu T.-K. Nguyen and Y. Fang. On generalized degree fairness in graph neural networks. arXiv preprint arXiv:\u00ac \u00ac. ."},{"key":"e_1_2_1_36_1","unstructured":"J. Ma J. Deng and Q. Mei. Subgroup generalization and fairness of graph neural networks. NeurIPS -: \u00ac -- ."},{"key":"e_1_2_1_37_1","volume-title":"WSDM","author":"Ma J.","unstructured":"J. Ma, R. Guo, M. Wan, L. Yang, A. Zhang, and J. Li. Learning fair node representations with graph counterfactual fairness. In WSDM, pages -- , ."},{"key":"e_1_2_1_38_1","unstructured":"P. V. Marsden. Egocentric and sociocentric measures of network centrality. Social networks ."},{"key":"e_1_2_1_39_1","unstructured":"N. Mehrabi F. Morstatter N. Saxena K. Lerman and A. Galstyan. A survey on bias and fairness in machine learning. arXiv preprint arXiv:\u00ac . ."},{"key":"e_1_2_1_40_1","unstructured":"D. Q. Nguyen V. Tong D. Phung and D. Q. Nguyen. Node co-occurrence based graph neural networks for knowledge graph link prediction. In WSDM ."},{"key":"e_1_2_1_41_1","unstructured":"D. Pessach and E. Shmueli. Algorithmic fairness. arXiv preprint arXiv: \u00ac. ."},{"key":"e_1_2_1_42_1","volume-title":"The perron-frobenius theorem: some of its applications","author":"Pillai S. U.","unstructured":"S. U. Pillai, T. Suel, and S. Cha. The perron-frobenius theorem: some of its applications. IEEE Signal Processing Magazine, ( ): -- , ."},{"key":"e_1_2_1_43_1","unstructured":"T. Rahman B. Surma M. Backes and Y. Zhang. Fairwalk: towards fair graph embedding. In IJCAI ."},{"key":"e_1_2_1_44_1","unstructured":"G. Sabidussi. The centrality index of a graph. Psychometrika (\u00ac): -- ."},{"key":"e_1_2_1_45_1","volume-title":"International conference on artificial neural networks","author":"Scherer D.","unstructured":"D. Scherer, A. M\u00fcller, and S. Behnke. Evaluation of pooling operations in convolutional architectures for object recognition. In International conference on artificial neural networks, pages -- . Springer, ."},{"key":"e_1_2_1_46_1","unstructured":"O. Shchur M. Mumme A. Bojchevski and S. G\u00fcnnemann. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:\u00ac \u00ac\u00ac. ."},{"key":"e_1_2_1_47_1","unstructured":"Y. Shi Y. Dong Q. Tan J. Li and N. Liu. Gigamae: Generalizable graph masked autoencoder via collaborative latent space reconstruction. In ACM CIKM ."},{"key":"e_1_2_1_48_1","unstructured":"H. Shomer W. Jin W. Wang and J. Tang. Toward degree bias in embedding-based knowledge graph completion. arXiv preprint arXiv: . ."},{"key":"e_1_2_1_49_1","volume-title":"SIGKDD","author":"Song W.","unstructured":"W. Song, Y. Dong, N. Liu, and J. Li. Guide: Group equality informed individual fairness in graph neural networks. In SIGKDD, pages -- \u00ac, ."},{"key":"e_1_2_1_50_1","unstructured":"Q. Tan N. Liu and X. Hu. Deep representation learning for social network analysis. Frontiers in Big Data : ."},{"key":"e_1_2_1_51_1","volume-title":"ACM International Conference on Web Search and Data Mining","author":"Tan Q.","unstructured":"Q. Tan, X. Zhang, N. Liu, D. Zha, L. Li, R. Chen, S.-H. Choi, and X. Hu. Bring your own view: Graph neural networks for link prediction with personalized subgraph selection. In ACM International Conference on Web Search and Data Mining, pages -- , ."},{"key":"e_1_2_1_52_1","unstructured":"X. Tang H. Yao Y. Sun Y. Wang J. Tang C. Aggarwal P. Mitra and S. Wang. Investigating and mitigating degree-related biases in graph convoltuional networks. In CIKM ."},{"key":"e_1_2_1_53_1","unstructured":"Everything is connected: Graph neural networks. Current Opinion in Structural Biology : ."},{"key":"e_1_2_1_54_1","unstructured":"G. Cucurull A. Casanova A. Romero P. Lio and Y. Bengio. Graph attention networks. arXiv preprint arXiv:\u00ac \u00ac .\u00ac ."},{"key":"e_1_2_1_55_1","unstructured":"R.Wang X.Wang C. Shi and L. Song. Uncovering the structural fairness in graph contrastive learning. arXiv preprint arXiv: \u00ac . \u00ac\u00ac ."},{"key":"e_1_2_1_56_1","unstructured":"Y. Wang Y. Zhao Y. Dong H. Chen J. Li and T. Derr. Improving fairness in graph neural networks via mitigating sensitive attribute leakage. In ACM SIGKDD ."},{"key":"e_1_2_1_57_1","unstructured":"[ ] F. Wu T. Zhang A. H. d. Souza Jr C. Fifty T. Yu and K. Q. Weinberger. Simplifying graph convolutional networks. arXiv preprint arXiv:\u00ac . \u00ac ."},{"key":"e_1_2_1_58_1","volume-title":"Graph Neural Networks: Foundations, Frontiers, and Applications","author":"Wu L.","unstructured":"L.Wu, P. Cui, J. Pei, L. Zhao, and L. Song. Graph neural networks. In Graph Neural Networks: Foundations, Frontiers, and Applications, pages -- . Springer, ."},{"key":"e_1_2_1_59_1","volume-title":"A comprehensive survey on graph neural networks","author":"Wu Z.","unstructured":"Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and S. Y. Philip. A comprehensive survey on graph neural networks. IEEE TNNLS, ."},{"key":"e_1_2_1_60_1","unstructured":"Z. Yang W. W. Cohen and R. Salakhutdinov. Revisiting semi-supervised learning with graph embeddings. arXiv preprint arXiv:\u00ac . \u00ac ."},{"key":"e_1_2_1_61_1","volume-title":"International conference on machine learning","author":"You J.","unstructured":"J. You, R. Ying, and J. Leskovec. Position-aware graph neural networks. In International conference on machine learning, pages \u00ac-- \u00ac . PMLR, ."},{"key":"e_1_2_1_62_1","unstructured":"M. B. Zafar I. Valera M. G. Rodriguez and K. P. Gummadi. Fairness constraints: Mechanisms for fair classification. arXiv preprint arXiv:\u00ac . ."},{"key":"e_1_2_1_63_1","unstructured":"B. H. Zhang B. Lemoine and M. Mitchell. Mitigating unwanted biases with adversarial learning. In AIES ."},{"key":"e_1_2_1_64_1","unstructured":"C. Zhang C. Huang Y. Li X. Zhang Y. Ye and C. Zhang. Look twice as much as you say: Scene graph contrastive learning for self-supervised image caption generation. In CIKM ."},{"key":"e_1_2_1_65_1","unstructured":"W. Zhang J. C.Weiss S. Zhou and T.Walsh. Fairness amidst non-iid graph data: A literature review. arXiv preprint arXiv: . \u00ac ."},{"key":"e_1_2_1_66_1","unstructured":"X. Zhang Q. Tan X. Huang and B. Li. Graph contrastive learning with personalized augmentation. arXiv preprint arXiv: . ."},{"key":"e_1_2_1_67_1","volume-title":"Deep learning on graphs: A survey","author":"Zhang Z.","unstructured":"Z. Zhang, P. Cui, and W. Zhu. Deep learning on graphs: A survey. IEEE TKDE, ."},{"key":"e_1_2_1_68_1","unstructured":"Z. Zhang F. Zhuang H. Zhu Z. Shi H. Xiong and Q. He. Relational graph neural network with hierarchical attention for knowledge graph completion. In AAAI ."},{"key":"e_1_2_1_69_1","unstructured":"J. Zhou G. Cui S. Hu Z. Zhang C. Yang Z. Liu L. Wang C. Li and M. Sun. Graph neural networks: A review of methods and applications. AI Open : -- ."}],"container-title":["ACM SIGKDD Explorations Newsletter"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3655103.3655105","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3655103.3655105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:52Z","timestamp":1750291432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3655103.3655105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,26]]},"references-count":69,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,3,26]]}},"alternative-id":["10.1145\/3655103.3655105"],"URL":"https:\/\/doi.org\/10.1145\/3655103.3655105","relation":{},"ISSN":["1931-0145","1931-0153"],"issn-type":[{"value":"1931-0145","type":"print"},{"value":"1931-0153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,26]]},"assertion":[{"value":"2024-03-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}