{"type":"ScholarlyArticle","title":"FairGT: A Fairness-aware Graph Transformer","authors":[{"name":"Renqiang Luo","slug":"renqiang-luo","given":"Renqiang","family":"Luo","affiliation":"Dalian University of Technology , China"},{"name":"Huafei Huang","slug":"huafei-huang","given":"Huafei","family":"Huang","affiliation":"Dalian University of Technology , China"},{"name":"Shuo Yu","slug":"shuo-yu","given":"Shuo","family":"Yu","affiliation":"Dalian University of Technology , China"},{"name":"Xiuzhen Zhang","slug":"xiuzhen-zhang","given":"Xiuzhen","family":"Zhang","affiliation":"RMIT University , Australia"},{"name":"Feng Xia","slug":"feng-xia","given":"Feng","family":"Xia","affiliation":"RMIT University , Australia"}],"abstract":"The design of Graph Transformers (GTs) often neglects considerations for fairness, resulting in biased outcomes against certain sensitive subgroups. Since GTs encode graph information without relying on message-passing mechanisms, conventional fairness-aware graph learning methods are not directly applicable to address these issues. To tackle this challenge, we propose FairGT, a Fairness-aware Graph Transformer explicitly crafted to mitigate fairness concerns inherent in GTs. FairGT incorporates a meticulous structural feature selection strategy and a multi-hop node feature integration method, ensuring independence of sensitive features and bolstering fairness considerations. These fairness-aware graph information encodings seamlessly integrate into the Transformer framework for downstream tasks. We also prove that the proposed fair structural topology encoding with adjacency matrix eigenvector selection and multi-hop integration are theoretically effective. Empirical evaluations conducted across five real-world datasets demonstrate FairGT's superiority in fairness metrics over existing graph transformers, graph neural networks, and state-of-the-art fairness-aware graph learning approaches.","doi":"10.24963/ijcai.2024/50","url":"https://ijcai.org/proceedings/2024/50","pdf":"https://ijcai.org/proceedings/2024/0050.pdf","markdown":"https://ijcai.org/proceedings/2024/50.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/50","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":50,"pages":{"first":449,"last":457},"keywords":["Data Mining: DM: Mining graphs","Machine Learning: ML: Trustworthy machine learning","AI Ethics, Trust, Fairness: ETF: Fairness and diversity"],"videos":[],"references":[{"position":1,"raw":"[Agarwal et al., 2021] Chirag Agarwal, Himabindu Lakkaraju, and Marinka Zitnik. Towards a unified framework for fair and stable graph representation learning. In UAI, pages 2114-2124, 2021.","title":"Towards a unified framework for fair and stable graph representation learning","authors":"Chirag Agarwal, Himabindu Lakkaraju, Marinka Zitnik","year":"2021","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Asuncion and Newman, 2007] Arthur Asuncion and David Newman. Uci machine learning repository, 2007.","title":"Arthur Asuncion and David Newman","authors":"Asuncion, Newman","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bo et al., 2023] Deyu Bo, Chuan Shi, Lele Wang, and Ren- jie Liao. Specformer: Spectral graph neural networks meet transformers. In ICLR, 2023.","title":"Specformer: Spectral graph neural networks meet transformers","authors":"Deyu Bo, Chuan Shi, Lele Wang, Renjie Liao","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Caton and Haas, 2023] Simon Caton and Christian Haas. Fairness in machine learning: A survey. ACM Computing Surveys, 2023.","title":"Fairness in machine learning: A survey","authors":"Haas Caton, Simon Caton, Christian Haas","year":"2023","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2020] Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, and Yaliang Li. Simple and deep graph convolutional networks. In ICML, pages 1725- 1735, 2020.","title":"Simple and deep graph convolutional networks","authors":"Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, Yaliang Li","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2023] Jinsong Chen, Kaiyuan Gao, Gaichao Li, and Kun He. NAGphormer: A tokenized graph trans- former for node classifcation in large graphs. In ICLR, 2023.","title":"NAGphormer: A tokenized graph transformer for node classifcation in large graphs","authors":"Jinsong Chen, Kaiyuan Gao, Gaichao Li, Kun He","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cheng et al., 2024] Debo Cheng, Jiuyong Li, Lin Liu, Jixue Liu, and Thuc Duy Le. Data-driven causal effect estima- tion based on graphical causal modelling: A survey. ACM Computing Surveys, 56(5):1-37, 2024.","title":"Data-driven causal effect estimation based on graphical causal modelling: A survey","authors":"Debo Cheng, Jiuyong Li, Lin Liu, Jixue Liu, Thuc Duy, Le","year":"2024","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cong et al., 2023] Zicun Cong, Baoxu Shi, Shan Li, Jaewon Yang, Qi He, and Pei Jian. FairSample: Training fair and accurate graph convolutional neural networks efficiently. IEEE Transactions on Knowledge and Data Engineering, pages 1-14, 2023.","title":"FairSample: Training fair and accurate graph convolutional neural networks efficiently","authors":"Cong","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dai and Wang, 2021] Enyan Dai and Suhang Wang. Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. In WSDM, pages 680-688, 2021.","title":"Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information","authors":"Wang ; ] Enyan Dai, Suhang Dai, Wang","year":"2021","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Dai and Wang, 2023] Enyan Dai and Suhang Wang. Learn- ing fair graph neural networks with limited and pri- vate sensitive attribute information. IEEE Transactions on Knowledge and Data Engineering, 35(7):7103-7117, 2023.","title":"Learning fair graph neural networks with limited and private sensitive attribute information","authors":"Wang ; ] Enyan Dai, Suhang Dai, Wang","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dong et al., 2023a] Yushun Dong, Jing Ma, Song Wang, Chen Chen, and Jundong Li. Fairness in graph mining: A survey. IEEE Transactions on Knowledge and Data En- gineering, 35(01):10583-10602, 2023.","title":"Fairness in graph mining: A survey","authors":"Dong","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Dong et al., 2023b] Yushun Dong, Song Wang, Jing Ma, Ninghao Liu, and Jundong Li. Interpreting unfairness in graph neural networks via training node attribution. In AAAI, pages 7441-7449, 2023.","title":"Interpreting unfairness in graph neural networks via training node attribution","authors":"Dong","year":"2023","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Dwivedi and Bresson, 2020] Vijay Prakash Dwivedi and Xavier Bresson. A generalization of transformer networks to graphs. arXiv preprint arXiv:2012.09699, 2020.","title":"A generalization of transformer networks to graphs","authors":"Vijay Prakash, Dwivedi, Xavier Bresson","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Dwork et al., 2012] Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard S. Zemel. Fairness through awareness. In ITCS, pages 214-226, 2012.","title":"Fairness through awareness","authors":"Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, Richard S Zemel","year":"2012","venue":"ITCS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Guo et al., 2023a] Dongliang Guo, Zhixuan Chu, and Sheng Li. Fair attribute completion on graph with miss- ing attributes. In ICLR, 2023.","title":"Fair attribute completion on graph with missing attributes","authors":"Guo","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Guo et al., 2023b] Xiaojun Guo, Yifei Wang, Tianqi Du, and Yisen Wang. Contranorm: A contrastive learning per- spective on oversmoothing and beyond. In ICLR, 2023.","title":"Contranorm: A contrastive learning perspective on oversmoothing and beyond","authors":"Guo","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[He et al., 2023] Xiaoxin He, Bryan Hooi, Thomas Laurent, Adam Perold, Yann LeCun, and Xavier Bresson. A gen- eralization of vit/mlp-mixer to graphs. In ICML, pages 12724-12745, 2023.","title":"A generalization of vit/mlp-mixer to graphs","authors":"Xiaoxin He, Bryan Hooi, Thomas Laurent, Adam Perold, Yann Lecun, Xavier Bresson","year":"2023","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[I-cheng and Che-hui, 2009] Yeh I-cheng and Lien Che-hui. The comparisons of data mining techniques for the pre- dictive accuracy of probability of default of credit card clients. Expert Systems with Applications, 36(2):2473- 2480, 2009.","title":"The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients","authors":"I-Cheng Yeh, Lien Che-Hui","year":"2009","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Jordan and Freiburger, 2015] Kareem L Jordan and Tina L Freiburger. The effect of race/ethnicity on sentencing: Ex- amining sentence type, jail length, and prison length. Jour- nal of Ethnicity in Criminal Justice, 13(3):179-196, 2015.","title":"The effect of race/ethnicity on sentencing: Examining sentence type, jail length, and prison length","authors":"L Kareem, Tina L Jordan, Freiburger","year":"2015","venue":"Journal of Ethnicity in Criminal Justice","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Kipf and Welling, 2017] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Kreuzer et al., 2021] Devin Kreuzer, Dominique Beaini, William L. Hamilton, Vincent Letourneau, and Prudencio Tossou. Rethinking graph transformers with spectral at- tention. In NeurIPS, pages 21618-21629, 2021.","title":"Rethinking graph transformers with spectral attention","authors":"Devin Kreuzer, Dominique Beaini, William L Hamilton, Vincent Letourneau, Prudencio Tossou","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lehoucq et al., 1998] Richard B. Lehoucq, Danny C. Sorensen, and Chao Yang. ARPACK users' guide -so- lution of large-scale eigenvalue problems with implicitly restarted Arnoldi methods. Software, environments, tools. SIAM, 1998.","title":"ARPACK users' guide -solution of large-scale eigenvalue problems with implicitly restarted Arnoldi methods","authors":"Richard B Lehoucq, Danny C Sorensen, Chao Yang","year":"1998","venue":"Software, environments, tools","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Ling et al., 2023] Hongyi Ling, Zhimeng Jiang, Youzhi Luo, Shuiwang Ji, and Na Zou. Learning fair graph rep- resentations via automated data augmentations. In ICLR, 2023.","title":"Learning fair graph representations via automated data augmentations","authors":"Hongyi Ling, Zhimeng Jiang, Youzhi Luo, Shuiwang Ji, Na Zou","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Liu et al., 2023] Chuang Liu, Yibing Zhan, Xueqi Ma, Liang Ding, Dapeng Tao, Jia Wu, and Wenbin Hu. Gap- former: Graph transformer with graph pooling for node classification. In IJCAI, 2023.","title":"Gapformer: Graph transformer with graph pooling for node classification","authors":"Chuang Liu, Yibing Zhan, Xueqi Ma, Liang Ding, Dapeng Tao, Jia Wu, Wenbin Hu","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/244"},{"position":25,"raw":"[Mehrabi et al., 2021] Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. A survey on bias and fairness in machine learning. ACM Computing Surveys, 54(6):1-35, 2021.","title":"A survey on bias and fairness in machine learning","authors":"Mehrabi","year":"2021","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Ren et al., 2023] Jing Ren, Feng Xia, Ivan Lee, Azadeh Noori Hoshyar, and Charu Aggarwal. Graph learning for anomaly analytics: Algorithms, applications, and chal- lenges. ACM Transactions on Intelligent Systems and Technology, 14(2):1-29, 2023.","title":"Graph learning for anomaly analytics: Algorithms, applications, and challenges","authors":"Jing Ren, Feng Xia, Ivan Lee, Azadeh Noori Hoshyar, Charu Aggarwal","year":"2023","venue":"ACM Transactions on Intelligent Systems and Technology","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Velickovic et al., 2018] Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. In NeurIPS, page 4, 2018.","title":"Graph attention networks","authors":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2022] Lei Wang, Shuo Yu, Falih Gozi Febri- nanto, Fayez Alqahtani, and Tarek E. EI-Tobely. Fairness- aware predictive graph learning in social networks. Math- ematics, 10(15):2696, 2022.","title":"Fairnessaware predictive graph learning in social networks","authors":"Lei Wang, Shuo Yu, Falih Gozi Febrinanto, Fayez Alqahtani, Tarek E Ei-Tobely","year":"2022","venue":"Mathematics","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wu et al., 2021] Zhanhao Wu, Paras Jain, Mattew A. Wright, Azalia Mirhoseini, Joseph E. Gonzalez, and Ion Stoica. Representing long-range context for graph neural networks with global attention. In NeurIPS, pages 13266- 13279, 2021.","title":"Representing long-range context for graph neural networks with global attention","authors":"Zhanhao Wu, Paras Jain, Mattew A Wright, Azalia Mirhoseini, Joseph E Gonzalez, Ion Stoica","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wu et al., 2023] Yi Wu, Yangyang Xu, Wenhao Zhu, Guo- jie Song, Zhouchen Lin, Liang Wang, and Shaoguo Liu. KDLGT: A linear graph transformer framework via kernel decomposition approach. In IJCAI, 2023.","title":"KDLGT: A linear graph transformer framework via kernel decomposition approach","authors":"Yi Wu, Yangyang Xu, Wenhao Zhu, Guojie Song, Zhouchen Lin, Liang Wang, Shaoguo Liu","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/263"},{"position":32,"raw":"[Xia et al., 2021] Feng Xia, Ke Sun, Shuo Yu, Abdul Aziz, Liangtian Wan, Shirui Pan, and Huan Liu. Graph learning: A survey. IEEE Transactions on Artificial Intelligence, 2(2):109-127, 2021.","title":"Graph learning: A survey","authors":"Feng Xia, Ke Sun, Shuo Yu, Abdul Aziz, Liangtian Wan, Shirui Pan, Huan Liu","year":"2021","venue":"IEEE Transactions on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Yin and Zhong, 2023] Shuo Yin and Guoqiang Zhong. LGI-GT:graph Transformers with local and global oper- ators interleaving. In IJCAI, 2023.","title":"LGI-GT:graph Transformers with local and global operators interleaving","authors":"Shuo Yin, Guoqiang Zhong","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/501"},{"position":34,"raw":"[Ying et al., 2021] Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Yanming Shen, and Tie- Yan Liu. Do transformers really perform badly for graph representation? In NeurIPS, pages 28877-28888, 2021.","title":"Do transformers really perform badly for graph representation?","authors":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Yanming Shen, Tie-Yan Liu","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhang et al., 2022] Zaixi Zhang, Qi Liu, Qingyong Hu, and Chee-Kong Lee. Hierarchical graph transformer with adaptive node sampling. In NeurIPS, pages 21171-21183, 2022.","title":"Hierarchical graph transformer with adaptive node sampling","authors":"Zhang","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhang et al., 2024] Guixian Zhang, Debo Cheng, Guan Yuan, and Shichao Zhang. Learning fair representations via rebalancing graph structure. Information Processing & Management, 61(1), 2024.","title":"Learning fair representations via rebalancing graph structure","authors":"Zhang","year":"2024","venue":"Information Processing & Management","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zhu et al., 2023] Wenhao Zhu, Tianyu Wen, Guojie Song, Xiaojun Ma, and Liang Wang. Hierarchical transformer for scalable graph learning. In IJCAI, 2023.","title":"Hierarchical transformer for scalable graph learning","authors":"Wenhao Zhu, Tianyu Wen, Guojie Song, Xiaojun Ma, Liang Wang","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/523"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}