Mitigating Relational Bias on Knowledge Graphs

TL;DR

This paper introduces Fair-KGNN, a novel framework designed to reduce multi-hop relational bias in knowledge graph neural networks, effectively mitigating discrimination while maintaining predictive accuracy across various datasets.

Contribution

The paper presents a generalizable framework, Fair-KGNN, that addresses multi-hop relational bias in KGNNs, extending beyond entity-wise bias mitigation.

Findings

Fair-KGNN effectively reduces gender-occupation bias.

Fair-KGNN mitigates nationality-salary bias.

The framework preserves KGNN predictive performance.

Abstract

Knowledge graph data are prevalent in real-world applications, and knowledge graph neural networks (KGNNs) are essential techniques for knowledge graph representation learning. Although KGNN effectively models the structural information from knowledge graphs, these frameworks amplify the underlying data bias that leads to discrimination towards certain groups or individuals in resulting applications. Additionally, as existing debiasing approaches mainly focus on the entity-wise bias, eliminating the multi-hop relational bias that pervasively exists in knowledge graphs remains an open question. However, it is very challenging to eliminate relational bias due to the sparsity of the paths that generate the bias and the non-linear proximity structure of knowledge graphs. To tackle the challenges, we propose Fair-KGNN, a KGNN framework that simultaneously alleviates multi-hop bias and preserves the proximity information of entity-to-relation in knowledge graphs. The proposed framework is generalizable to mitigate the relational bias for all types of KGNN. We develop two instances of Fair-KGNN incorporating with two state-of-the-art KGNN models, RGCN and CompGCN, to mitigate gender-occupation and nationality-salary bias. The experiments carried out on three benchmark knowledge graph datasets demonstrate that the Fair-KGNN can effectively mitigate unfair situations during representation learning while preserving the predictive performance of KGNN models.