CUED Publications database

CrossWalk: Fairness-enhanced Node Representation Learning

Khajehnejad, A and Khajehnejad, M and Babaei, M and Gummadi, KP and Weller, A and Mirzasoleiman, B CrossWalk: Fairness-enhanced Node Representation Learning. (Unpublished)

Full text not available from this repository.

Abstract

The potential for machine learning systems to amplify social inequities and unfairness is receiving increasing popular and academic attention. Much recent work has focused on developing algorithmic tools to assess and mitigate such unfairness. However, there is little work on enhancing fairness in graph algorithms. Here, we develop a simple, effective and general method, CrossWalk, that enhances fairness of various graph algorithms, including influence maximization, link prediction and node classification, applied to node embeddings. CrossWalk is applicable to any random walk based node representation learning algorithm, such as DeepWalk and Node2Vec. The key idea is to bias random walks to cross group boundaries, by upweighting edges which (1) are closer to the groups' peripheries or (2) connect different groups in the network. CrossWalk pulls nodes that are near groups' peripheries towards their neighbors from other groups in the embedding space, while preserving the necessary structural information from the graph. Extensive experiments show the effectiveness of our algorithm to enhance fairness in various graph algorithms, including influence maximization, link prediction and node classification in synthetic and real networks, with only a very small decrease in performance.

Item Type: Article
Uncontrolled Keywords: cs.LG cs.LG cs.SI stat.ML
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 14 May 2021 20:05
Last Modified: 03 Jun 2021 05:34
DOI: