Mitigating Degree Bias in Signed Graph Neural Networks

TL;DR

This paper investigates fairness issues in Signed Graph Neural Networks caused by degree bias, proposing a novel degree debiasing method that improves node representation fairness without sacrificing performance.

Contribution

It introduces DD-SGNN, a model-agnostic approach to mitigate degree bias in SGNNs, expanding fairness research from GNNs to signed graphs.

Findings

DD-SGNN effectively reduces degree bias in signed graphs

The method maintains or improves classification performance

Experiments on four real-world datasets validate the approach

Abstract

Like Graph Neural Networks (GNNs), Signed Graph Neural Networks (SGNNs) are also up against fairness issues from source data and typical aggregation method. In this paper, we are pioneering to make the investigation of fairness in SGNNs expanded from GNNs. We identify the issue of degree bias within signed graphs, offering a new perspective on the fairness issues related to SGNNs. To handle the confronted bias issue, inspired by previous work on degree bias, a new Model-Agnostic method is consequently proposed to enhance representation of nodes with different degrees, which named as Degree Debiased Signed Graph Neural Network (DD-SGNN) . More specifically, in each layer, we make a transfer from nodes with high degree to nodes with low degree inside a head-to-tail triplet, which to supplement the underlying domain missing structure of the tail nodes and meanwhile maintain the positive and negative semantics specified by balance theory in signed graphs. We make extensive experiments on four real-world datasets. The result verifies the validity of the model, that is, our model mitigates the degree bias issue without compromising performance($\textit{i.e.}$, AUC, F1). The code is provided in supplementary material.