ABSTRACT
Graph Neural Networks (GNNs) have demonstrated a great representation learning capability on graph data and have been utilized in various downstream applications. However, real-world data in web-based applications (e.g., recommendation and advertising) always contains bias, preventing GNNs from learning fair representations. Although many works were proposed to address the fairness issue, they suffer from the significant problem of insufficient learnable knowledge with limited attributes after debiasing. To address this problem, we develop Graph-Fairness Mixture of Experts (G-Fame), a novel plug-and-play method to assist any GNNs to learn distinguishable representations with unbiased attributes. Furthermore, based on G-Fame, we propose G-Fame++, which introduces three novel strategies to improve the representation fairness from node representations, model layer, and parameter redundancy perspectives. In particular, we first present the embedding diversified method to learn distinguishable node representations. Second, we design the layer diversified strategy to maximize the output difference of distinct model layers. Third, we introduce the expert diversified method to minimize expert parameter similarities to learn diverse and complementary representations. Extensive experiments demonstrate the superiority of G-Fame and G-Fame++ in both accuracy and fairness, compared to state-of-the-art methods across multiple graph datasets.
- Yahav Bechavod, Christopher Jung, and Steven Z Wu. 2020. Metric-free individual fairness in online learning. In NeurIPS.Google Scholar
- Alex Beutel, Jilin Chen, Zhe Zhao, and Ed H Chi. 2017. Data decisions and theoretical implications when adversarially learning fair representations. arXiv preprint arXiv:1707.00075 (2017).Google Scholar
- Reuben Binns. 2020. On the apparent conflict between individual and group fairness. In FAccT.Google Scholar
- Robin Burke. 2017. Multisided fairness for recommendation. arXiv preprint arXiv:1707.00093 (2017).Google Scholar
- Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, and Yaliang Li. 2020. Simple and deep graph convolutional networks. In ICML.Google Scholar
- Sean Current, Yuntian He, Saket Gurukar, and Srinivasan Parthasarathy. 2022. FairMod: Fair Link Prediction and Recommendation via Graph Modification. arXiv preprint arXiv:2201.11596 (2022).Google Scholar
- Enyan Dai and Suhang Wang. 2021. Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. In WSDM.Google Scholar
- Yushun Dong, Song Wang, Yu Wang, Tyler Derr, and Jundong Li. 2022. On Structural Explanation of Bias in Graph Neural Networks. In KDD.Google Scholar
- Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. 2012. Fairness through awareness. In ITCS.Google Scholar
- Harrison Edwards and Amos Storkey. 2015. Censoring representations with an adversary. arXiv preprint arXiv:1511.05897 (2015).Google Scholar
- Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin. 2019. Graph neural networks for social recommendation. In WWW.Google Scholar
- Yujie Fan, Mingxuan Ju, Chuxu Zhang, and Yanfang Ye. 2022. Heterogeneous temporal graph neural network. In SDM.Google Scholar
- Will Fleisher. 2021. What’s Fair about Individual Fairness¿. In AAAI.Google Scholar
- Arpita Ghosh and Robert Kleinberg. 2016. Inferential privacy guarantees for differentially private mechanisms. arXiv preprint arXiv:1603.01508 (2016).Google Scholar
- Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. In ICML.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM (2020).Google Scholar
- Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In KDD.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In NeurIPS.Google Scholar
- Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. In NeurIPS.Google Scholar
- Zhimeng Jiang, Xiaotian Han, Chao Fan, Fan Yang, Ali Mostafavi, and Xia Hu. 2022. Generalized Demographic Parity for Group Fairness. In ICLR.Google Scholar
- Jian Kang and Hanghang Tong. 2021. Fair graph mining. In ICDM.Google Scholar
- Jian Kang, Tiankai Xie, Xintao Wu, Ross Maciejewski, and Hanghang Tong. 2021. MultiFair: Multi-Group Fairness in Machine Learning. arXiv preprint arXiv:2105.11069 (2021).Google Scholar
- Shima Khoshraftar and Aijun An. 2022. A Survey on Graph Representation Learning Methods. arXiv preprint arXiv:2204.01855 (2022).Google Scholar
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR.Google Scholar
- Thomas N Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016).Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.Google Scholar
- Guohao Li, Matthias Muller, Ali Thabet, and Bernard Ghanem. 2019. Deepgcns: Can gcns go as deep as cnns¿. In ICCV.Google Scholar
- Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, and Tom Goldstein. 2018. Visualizing the loss landscape of neural nets. In NeurIPS.Google Scholar
- Peizhao Li, Yifei Wang, Han Zhao, Pengyu Hong, and Hongfu Liu. 2021. On dyadic fairness: Exploring and mitigating bias in graph connections. In ICLR.Google Scholar
- Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi Jaakkola, Geoffrey J Gordon, Stefanie Jegelka, and Ruslan Salakhutdinov. 2021. Information obfuscation of graph neural networks. In ICML.Google Scholar
- Weiyang Liu, Rongmei Lin, Zhen Liu, Li Xiong, Bernhard Schölkopf, and Adrian Weller. 2021. Learning with hyperspherical uniformity. In AISTATS.Google Scholar
- Sepideh Mahabadi and Ali Vakilian. 2020. Individual fairness for k-clustering. In ICML.Google Scholar
- Farzan Masrour, Tyler Wilson, Heng Yan, Pang-Ning Tan, and Abdol Esfahanian. 2020. Bursting the filter bubble: Fairness-aware network link prediction. In AAAI.Google Scholar
- Dana Pessach and Erez Shmueli. 2022. A Review on Fairness in Machine Learning. Comput. Surveys (2022).Google Scholar
- Tahleen Rahman, Bartlomiej Surma, Michael Backes, and Yang Zhang. 2019. Fairwalk: Towards fair graph embedding. In IJCAI.Google Scholar
- Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. 2020. DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. In ICLR.Google Scholar
- Noam Shazeer, *Azalia Mirhoseini, *Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In ICLR.Google Scholar
- Indro Spinelli, Simone Scardapane, Amir Hussain, and Aurelio Uncini. 2021. Fairdrop: Biased edge dropout for enhancing fairness in graph representation learning. IEEE Transactions on Artificial Intelligence (2021).Google Scholar
- Yijun Tian, Kaiwen Dong, Chunhui Zhang, Chuxu Zhang, and Nitesh V Chawla. 2023. Heterogeneous Graph Masked Autoencoders. In AAAI.Google Scholar
- Yijun Tian, Chuxu Zhang, Zhichun Guo, Xiangliang Zhang, and Nitesh Chawla. 2023. Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency. In ICLR.Google Scholar
- Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of Machine Learning Research (2008).Google Scholar
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In ICLR.Google Scholar
- Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, and R Devon Hjelm. 2019. Deep Graph Infomax. In ICLR.Google Scholar
- Le Wu, Lei Chen, Pengyang Shao, Richang Hong, Xiting Wang, and Meng Wang. 2021. Learning fair representations for recommendation: A graph-based perspective. In WWW.Google Scholar
- Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, and Bin Cui. 2020. Graph neural networks in recommender systems: a survey. Comput. Surveys (2020).Google Scholar
- Lianghao Xia, Chao Huang, and Chuxu Zhang. 2022. Self-supervised hypergraph transformer for recommender systems. In KDD.Google Scholar
- Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks¿. In ICLR.Google Scholar
- Moyi Yang, Junjie Sheng, Xiangfeng Wang, Wenyan Liu, Bo Jin, Jun Wang, and Hongyuan Zha. 2022. Obtaining Dyadic Fairness by Optimal Transport. arXiv preprint arXiv:2202.04520 (2022).Google Scholar
- Sirui Yao and Bert Huang. 2017. Beyond parity: Fairness objectives for collaborative filtering. In NeurIPS.Google Scholar
- Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, and Krishna P Gummadi. 2017. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In WWW.Google Scholar
- Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez-Rodriguez, and Krishna P Gummadi. 2019. Fairness constraints: A flexible approach for fair classification. Journal of Machine Learning Research (2019).Google Scholar
- Chuxu Zhang, Dongjin Song, Chao Huang, Ananthram Swami, and Nitesh V Chawla. 2019. Heterogeneous graph neural network. In KDD.Google Scholar
- Chunhui Zhang, Yijun Tian, Mingxuan Ju, Zheyuan Liu, Yanfang Ye, Nitesh Chawla, and Chuxu Zhang. 2023. Chasing All-Round Graph Representation Robustness: Model, Training, and Optimization. In ICLR.Google Scholar
- Chuxu Zhang, Huaxiu Yao, Chao Huang, Meng Jiang, Zhenhui Li, and Nitesh V Chawla. 2020. Few-shot knowledge graph completion. In AAAI.Google Scholar
- Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. In NeurIPS.Google Scholar
Index Terms
- Fair Graph Representation Learning via Diverse Mixture-of-Experts
Recommendations
FairMILE: Towards an Efficient Framework for Fair Graph Representation Learning
EAAMO '23: Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms, Mechanisms, and OptimizationGraph representation learning models have demonstrated great capability in many real-world applications. Nevertheless, prior research indicates that these models can learn biased representations leading to discriminatory outcomes. A few works have been ...
Graph Representation Learning: Foundations, Methods, Applications and Systems
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningGraphs such as social networks and molecular graphs are ubiquitous data structures in the real world. Due to their prevalence, it is of great research importance to extract meaningful patterns from graph structured data so that downstream tasks can be ...
Efficient Fair Graph Representation Learning Using a Multi-level Framework
WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023Graph representation learning models have demonstrated great capability in many real-world applications. Nevertheless, prior research reveals that these models can learn biased representations leading to unfair outcomes. A few works have been proposed ...
Comments