Compositional Fairness Constraints for Graph Embeddings

Abstract

Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems. However, existing graph embedding techniques are unable to cope with fairness constraints, e.g., ensuring that the learned representations do not correlate with certain attributes, such as age or gender. Here, we introduce an adversarial framework to enforce fairness constraints on graph embeddings. Our approach is compositional---meaning that it can flexibly accommodate different combinations of fairness constraints during inference. For instance, in the context of social recommendations, our framework would allow one user to request that their recommendations are invariant to both their age and gender, while also allowing another user to request invariance to just their age. Experiments on standard knowledge graph and recommender system benchmarks highlight the utility of our proposed framework.

Proceedings of the 36th International Conference on Machine Learning, Long Beach, California, PMLR 97, 2019

References in corpus (10)

• Inductive Representation Learning on Large Graphs
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Graph Convolutional Matrix Completion
• Variational Graph Auto-Encoders
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Disentangling factors of variation in deep representations using adversarial training
• Learning Adversarially Fair and Transferable Representations
• On Formalizing Fairness in Prediction with Machine Learning
• Notes on Noise Contrastive Estimation and Negative Sampling
• New Fairness Metrics for Recommendation that Embrace Differences

Cited by in corpus (33)

• Personalized Counterfactual Fairness in Recommendation
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• CausPref: Causal Preference Learning for Out-of-Distribution Recommendation
• FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
• RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network
• Unbiased Graph Embedding with Biased Graph Observations
• A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Subgroup Generalization and Fairness of Graph Neural Networks
• DeBayes: a Bayesian Method for Debiasing Network Embeddings
• Towards a Unified Framework for Fair and Stable Graph Representation Learning
• Incorporating Experts' Judgment into Machine Learning Models
• User Consented Federated Recommender System Against Personalized Attribute Inference Attack
• Counterfactual Learning on Graphs: A Survey
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
• Does Gender Matter? Towards Fairness in Dialogue Systems
• Measuring Social Bias in Knowledge Graph Embeddings
• TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers
• Modeling Techniques for Machine Learning Fairness: A Survey
• FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently
• MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit
• Information Obfuscation of Graph Neural Networks
• Fair Clustering with Multiple Colors
• In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
• InfoFair: Information-Theoretic Intersectional Fairness
• Adversarial Learning for Debiasing Knowledge Graph Embeddings
• FairMILE: Towards an Efficient Framework for Fair Graph Representation Learning
• Fairness in Deep Learning: A Computational Perspective
• FAST: A Fairness Assured Service Recommendation Strategy Considering Service Capacity Constraint
• Information Access Equality on Network Generative Models