Unlearning Algorithmic Biases over Graphs

TL;DR

This paper introduces a lightweight, certifiable graph unlearning method that mitigates algorithmic bias in pre-trained graph models without retraining, offering a practical bias correction tool with performance guarantees.

Contribution

It presents a novel, training-free unlearning approach for bias mitigation in graph models, including fairness-aware feature unlearning and structural unlearning with bias-informed element removal.

Findings

Effective bias mitigation demonstrated on real networks

Minimal utility loss compared to retraining from scratch

Favorable utility-complexity trade-offs achieved

Abstract

The growing enforcement of the right to be forgotten regulations has propelled recent advances in certified (graph) unlearning strategies to comply with data removal requests from deployed machine learning (ML) models. Motivated by the well-documented bias amplification predicament inherent to graph data, here we take a fresh look at graph unlearning and leverage it as a bias mitigation tool. Given a pre-trained graph ML model, we develop a training-free unlearning procedure that offers certifiable bias mitigation via a single-step Newton update on the model weights. This way, we contribute a computationally lightweight alternative to the prevalent training- and optimization-based fairness enhancement approaches, with quantifiable performance guarantees. We first develop a novel fairness-aware nodal feature unlearning strategy along with refined certified unlearning bounds for this setting, whose impact extends beyond the realm of graph unlearning. We then design structural unlearning methods endowed with principled selection mechanisms over nodes and edges informed by rigorous bias analyses. Unlearning these judiciously selected elements can mitigate algorithmic biases with minimal impact on downstream utility (e.g., node classification accuracy). Experimental results over real networks corroborate the bias mitigation efficacy of our unlearning strategies, and delineate markedly favorable utility-complexity trade-offs relative to retraining from scratch using augmented graph data obtained via removals.