Abstract
Graph is a ubiquitous type of data that appears in many real-world applications, including social network analysis, recommendations and financial security. Important as it is, decades of research have developed plentiful computational models to mine graphs. Despite its prosperity, concerns with respect to the potential algorithmic discrimination have been grown recently. Algorithmic fairness on graphs, which aims to mitigate bias introduced or amplified during the graph mining process, is an attractive yet challenging research topic. The first challenge corresponds to the theoretical challenge, where the non-IID nature of graph data may not only invalidate the basic assumption behind many existing studies in fair machine learning, but also introduce new fairness definition(s) based on the inter-correlation between nodes rather than the existing fairness definition(s) in fair machine learning. The second challenge regarding its algorithmic aspect aims to understand how to balance the trade-off between model accuracy and fairness. This tutorial aims to (1) comprehensively review the state-of-the-art techniques to enforce algorithmic fairness on graphs and (2) enlighten the open challenges and future directions. We believe this tutorial could benefit researchers and practitioners from the areas of data mining, artificial intelligence and social science.
Slides
Schedule
- Time: 10:00am - 12:00pm CDT, April 28, 2023
- Location: Think 5
Outline
- Introduction
- Background and motivations
- Problem definitions and settings
- Key challenges
- Part I: Group Fairness on Graphs
- Fair graph ranking
- Fair graph clustering
- Fair graph embedding
- Part II: Individual Fairness on Graphs
- Optimization-based method
- Ranking-based method
- Part III: Other Fairness on Graphs
- Counterfactual fairness
- Degree fairness
- Part IV: Future Trends
- Fairness on dynamic graphs
- Benchmark and evaluation metrics
- Fairness vs. other social aspects
Speaker's Bio
Jian Kang Jian Kang is a final-year Ph.D. candidate in the Department of Computer Science at the University of Illinois at Urbana-Champaign advised by Dr. Hanghang Tong. He received his M.CS. degree from the University of Virginia in 2016 and B.Eng. degree from Beijing University of Posts and Telecommunications in 2014. His research interests lie in fair learning and mining on graphs. His works on related topics have been published at several top conferences and journals in data mining and artificial intelligence (e.g., ICLR, KDD, WWW, CIKM, TKDE, TVCG). He is the recipient of several highly competitive awards and honors, including Rising Star in Data Science by the University of Chicago, Rising Star in Data Mining and Management by Frontiers in Big Data, Mavis Future Faculty Fellowship by the University of Illinois at Urbana-Champaign and five best reviewer awards (ICML 2020, ICLR 2021, CIKM 2021, NeurIPS 2022, LOG 2022). For more information, please refer to his personal website at http://jiank2.web.illinois.edu.
Hanghang Tong is currently an associate professor at Department of Computer Science at University of Illinois at Urbana-Champaign. Before that, he worked at Arizona State University as an associate professor, at City University of New York (City College) as an assistant professor and at IBM T. J. Watson Research Center as a Research Staff Member. He received his Ph.D. from the Machine Learning Department of School of Computer Science at Carnegie Mellon University in 2009. His major research interest lies in large-scale data mining for graphs and multimedia. In the past, he have published 200+ papers at these areas and his research has received several awards, including SDM/IBM 2018 early career data mining research award, two 'test of time' awards (ICDM 2015 10-Year Highest Impact Paper award, ICDM 2022 10-Year Highest Impact Paper award), ICDM Tao Li award (2019), NSF CAREER award, several best paper awards (e.g., ICDM'06 best paper, SDM'08 best paper, CIKM'12 best paper, etc.). He was Editor-in-Chief of ACM SIGKDD Explorations (2018 - 2022). He is a fellow of IEEE (2022). For more information, please refere to his personal website at http://tonghanghang.org.
Remark
A longer version of this tutorial can be found here.
References
- Tsioutsiouliklis, S., Pitoura, E., Tsaparas, P., Kleftakis, I., Mamoulis, N. (2021). Fairness-aware PageRank. WWW 2021.
- Tsioutsiouliklis, S., Pitoura, E., Semertzidis, K., & Tsaparas, P. (2022). Link Recommendations for PageRank Fairness. WWW 2022.
- Kleindessner, M., Samadi, S., Awasthi, P., & Morgenstern, J. (2019). Guarantees for Spectral Clustering with Fairness Constraints. ICML 2019.
- Bose, A., & Hamilton, W. (2019). Compositional Fairness Constraints for Graph Embeddings. ICML 2019.
- Rahman, T., Surma, B., Backes, M., & Zhang, Y. (2019). Fairwalk: Towards Fair Graph Embedding. IJCAI 2019.
- Dai, E., & Wang, S. (2021). Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information. WSDM 2021.
- Kang, J., He, J., Maciejewski, R., & Tong, H. (2020). InFoRM: Individual Fairness on Graph Mining. KDD 2020.
- Dong, Y., Kang, J., Tong, H., & Li, J. (2021). Individual Fairness for Graph Neural Networks: A Ranking based Approach. KDD 2021.
- Agarwal, C., Lakkaraju, H., & Zitnik, M. (2021). Towards a Unified Framework for Fair and Stable Graph Representation Learning. UAI 2021.
- Tang, X., Yao, H., Sun, Y., Wang, Y., Tang, J., Aggarwal, C., … & Wang, S. (2020). Investigating and Mitigating Degree-related Biases in Graph Convolutional Networks. CIKM 2020.
- Kang, J., Zhu, Y., Xia, Y., Luo, J., & Tong, H. (2022). RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network. WWW 2022.