Unbiased Graph Embedding with Biased Graph Observations
arXiv:2110.13957 · doi:10.1145/3485447.3512189
Abstract
Graph embedding techniques are pivotal in real-world machine learning tasks that operate on graph-structured data, such as social recommendation and protein structure modeling. Embeddings are mostly performed on the node level for learning representations of each node. Since the formation of a graph is inevitably affected by certain sensitive node attributes, the node embeddings can inherit such sensitive information and introduce undesirable biases in downstream tasks. Most existing works impose ad-hoc constraints on the node embeddings to restrict their distributions for unbiasedness/fairness, which however compromise the utility of the resulting embeddings. In this paper, we propose a principled new way for unbiased graph embedding by learning node embeddings from an underlying bias-free graph, which is not influenced by sensitive node attributes. Motivated by this new perspective, we propose two complementary methods for uncovering such an underlying graph, with the goal of introducing minimum impact on the utility of the embeddings. Both our theoretical justification and extensive experimental comparisons against state-of-the-art solutions demonstrate the effectiveness of our proposed methods.
Keywords: unbiased graph embedding, fairness, sensitive attributes, bias-free graph, node representation In Proceedings of the ACM Web Conference 2022 (WWW'22), April 25-29, 2022, Virtual Event, Lyon, France. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3485447.3512189
References in corpus (7)
- Semi-Supervised Classification with Graph Convolutional Networks
- LINE: Large-scale Information Network Embedding
- BPR: Bayesian Personalized Ranking from Implicit Feedback
- Equality of Opportunity in Supervised Learning
- Simplifying Graph Convolutional Networks
- Kronecker Graphs: An Approach to Modeling Networks
- Compositional Fairness Constraints for Graph Embeddings
Cited by in corpus (4)
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
- Counterfactual Learning on Graphs: A Survey
- Globally Interpretable Graph Learning via Distribution Matching
- Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs