Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning
Staff - Faculty of Informatics
Date: 21 May 2021 / 16:00 - 17:00
Indro Spinelli, Università la Sapienza, Italy
Graph representation learning has become a ubiquitous component in many scenarios, ranging from social network analysis to energy forecasting in smart grids. In several applications, ensuring the fairness of the node (or graph) representations with respect to some protected attributes is crucial for their correct deployment. Yet, fairness in graph deep learning remains under-explored, with few solutions available. In particular, the tendency of similar nodes to cluster on several real-world graphs (i.e., homophily) can dramatically worsen the fairness of these procedures. In this paper, we propose a biased edge dropout algorithm (FairDrop) to counter-act homophily and improve fairness in graph representation learning. FairDrop can be plugged in easily on many existing algorithms, is efficient, adaptable, and can be combined with other fairness-inducing solutions. After describing the general algorithm, we demonstrate its application on two benchmark tasks, specifically, as a random walk model for producing node embeddings, and to a graph convolutional network for link prediction. We prove that the proposed algorithm can successfully improve the fairness of all models up to a small or negligible drop in accuracy, and compares favourably with existing state-of-the-art solutions. In an ablation study, we demonstrate that our algorithm can flexibly interpolate between biasing towards fairness and an unbiased edge dropout. Furthermore, to better evaluate the gains, we propose a new dyadic group definition to measure the bias of a link prediction task when paired with group-based fairness metrics. In particular, we extend the metric used to measure the bias in the node embeddings to take into account the graph structure.
Indro Spinelli is a PhD candidate at the ISPAMM lab of Sapienza University of Rome. He is working under the supervision of Dr. Simone Scardapane and Aurelio Uncini. His main interest is trustworthy machine learning for graph structered data and, more in general, anything that combines neural networks and graphs. Previously he was an intern at the Alcor Lab where his research focused on Computer Vision and Robotics (SLAM).
Host: Prof. Cesare Alippi
You can join here