MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit
arXiv:1909.11793
Abstract
Are Graph Neural Networks (GNNs) fair? In many real world graphs, the formation of edges is related to certain node attributes (e.g. gender, community, reputation). In this case, standard GNNs using these edges will be biased by this information, as it is encoded in the structure of the adjacency matrix itself. In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata. This bias implies an inability to control for important covariates in real-world applications, such as recommendation systems. To solve these issues, we introduce the Metadata-Orthogonal Node Embedding Training (MONET) unit, a general model for debiasing embeddings of nodes in a graph. MONET achieves this by ensuring that the node embeddings are trained on a hyperplane orthogonal to that of the node metadata. This effectively organizes unstructured embedding dimensions into an interpretable topology-only, metadata-only division with no linear interactions. We illustrate the effectiveness of MONET though our experiments on a variety of real world graphs, which shows that our method can learn and remove the effect of arbitrary covariates in tasks such as preventing the leakage of political party affiliation in a blog network, and thwarting the gaming of embedding-based recommendation systems.
References in corpus (7)
- Distributed Representations of Words and Phrases and their Compositionality
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- The ground truth about metadata and community detection in networks
- Structure and inference in annotated networks
- MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
- Compositional Fairness Constraints for Graph Embeddings
- A Tutorial on Network Embeddings
Cited by in corpus (5)
- EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
- Machine Learning on Graphs: A Model and Comprehensive Taxonomy
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
- Unbiased Graph Embedding with Biased Graph Observations
- DeBayes: a Bayesian Method for Debiasing Network Embeddings