Unlearning Algorithmic Biases over Graphs

• URL: http://arxiv.org/abs/2505.14945v1
• Date: Tue, 20 May 2025 22:12:53 GMT
• Title: Unlearning Algorithmic Biases over Graphs
• Authors: O. Deniz Kose, Gonzalo Mateos, Yanning Shen,
• Abstract summary: We take a fresh look at graph unlearning and leverage it as a bias mitigation tool.<n>We develop a training-free unlearning procedure that offers certifiable bias mitigation via a single-step Newton update on the model weights.<n>We then design structural unlearning methods endowed with principled selection mechanisms over nodes and edges informed by rigorous bias analyses.
• Score: 22.373465731963915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Federated Graph Unlearning [23.00839112398916]
  The demand for data privacy has led to the development of frameworks like Federated Graph Learning.<n>The proposed framework employs a bifurcated strategy tailored to the specific unlearning request.<n>The framework achieves substantial improvements in model prediction accuracy across both client and meta-unlearning scenarios.
  arXiv  Detail & Related papers  (2025-08-04T14:57:03Z)
• Attribute-to-Delete: Machine Unlearning via Datamodel Matching [65.13151619119782]
  Machine unlearning -- efficiently removing a small "forget set" training data on a pre-divertrained machine learning model -- has recently attracted interest. Recent research shows that machine unlearning techniques do not hold up in such a challenging setting.
  arXiv  Detail & Related papers  (2024-10-30T17:20:10Z)
• Erase then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning [17.85404473268992]
  Graph unlearning aims to eliminate the influence of nodes, edges, or attributes from a trained Graph Neural Network (GNN)<n>Existing graph unlearning techniques often necessitate additional training on the remaining data, leading to significant computational costs.<n>We propose a two-stage training-free approach, Erase then Rectify (ETR), designed for efficient and scalable graph unlearning.
  arXiv  Detail & Related papers  (2024-09-25T07:20:59Z)
• DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization [44.291382840373]
  This paper addresses the challenge of out-of-distribution generalization in graph machine learning. Traditional graph learning algorithms falter in real-world scenarios where this assumption fails. A principal factor contributing to this suboptimal performance is the inherent simplicity bias of neural networks.
  arXiv  Detail & Related papers  (2024-08-08T12:08:55Z)
• GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networks [69.97213941893351]
  The emergence of Graph Neural Networks (GNNs) in graph data analysis has raised critical concerns about data misuse during model training. Existing methodologies address either data misuse detection or mitigation, and are primarily designed for local GNN models. This paper introduces a pioneering approach called GraphGuard, to tackle these challenges.
  arXiv  Detail & Related papers  (2023-12-13T02:59:37Z)
• Gradient Surgery for One-shot Unlearning on Generative Model [0.989293617504294]
  We introduce a simple yet effective approach to remove a data influence on the deep generative model. Inspired by works in multi-task learning, we propose to manipulate gradients to regularize the interplay of influence among samples.
  arXiv  Detail & Related papers  (2023-07-10T13:29:23Z)
• Model Sparsity Can Simplify Machine Unlearning [33.18951938708467]
  In response to recent data regulation requirements, machine unlearning (MU) has emerged as a critical process. Our study introduces a novel model-based perspective: model sparsification via weight pruning. We show in both theory and practice that model sparsity can boost the multi-criteria unlearning performance of an approximate unlearner.
  arXiv  Detail & Related papers  (2023-04-11T02:12:02Z)
• Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism [65.46524775457928]
  offline reinforcement learning seeks to utilize offline/historical data to optimize sequential decision-making strategies. We study the statistical limits of offline reinforcement learning with linear model representations.
  arXiv  Detail & Related papers  (2022-03-11T09:00:12Z)
• Unbiased Graph Embedding with Biased Graph Observations [52.82841737832561]
  We propose a principled new way for obtaining unbiased representations by learning from an underlying bias-free graph. Based on this new perspective, we propose two complementary methods for uncovering such an underlying graph.
  arXiv  Detail & Related papers  (2021-10-26T18:44:37Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• Contrastive Learning for Fair Representations [50.95604482330149]
  Trained classification models can unintentionally lead to biased representations and predictions. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. We propose a method for mitigating bias by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations.
  arXiv  Detail & Related papers  (2021-09-22T10:47:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.