FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization

• URL: http://arxiv.org/abs/2403.12474v1
• Date: Tue, 19 Mar 2024 06:22:58 GMT
• Title: FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization
• Authors: Cheng Yang, Jixi Liu, Yunhe Yan, Chuan Shi,
• Abstract summary: We argue that filtering-based strategies may also filter out some non-sensitive feature information, leading to a sub-optimal trade-off between predictive performance and fairness. We unveil an innovative neutralization-based paradigm, where additional Fairness-facilitating Features (F3) are incorporated into node features or representations before message passing. We name our method as FairSIN, and present three implementation variants from both data-centric and model-centric perspectives.
• Score: 40.78945336901361
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the remarkable success of graph neural networks (GNNs) in modeling graph-structured data, like other machine learning models, GNNs are also susceptible to making biased predictions based on sensitive attributes, such as race and gender. For fairness consideration, recent state-of-the-art (SOTA) methods propose to filter out sensitive information from inputs or representations, e.g., edge dropping or feature masking. However, we argue that such filtering-based strategies may also filter out some non-sensitive feature information, leading to a sub-optimal trade-off between predictive performance and fairness. To address this issue, we unveil an innovative neutralization-based paradigm, where additional Fairness-facilitating Features (F3) are incorporated into node features or representations before message passing. The F3 are expected to statistically neutralize the sensitive bias in node representations and provide additional nonsensitive information. We also provide theoretical explanations for our rationale, concluding that F3 can be realized by emphasizing the features of each node's heterogeneous neighbors (neighbors with different sensitive attributes). We name our method as FairSIN, and present three implementation variants from both data-centric and model-centric perspectives. Experimental results on five benchmark datasets with three different GNN backbones show that FairSIN significantly improves fairness metrics while maintaining high prediction accuracies.

Related papers

• Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation [53.91958614666386]
  Unsupervised graph representation learning (UGRL) based on graph neural networks (GNNs) We propose a novel UGRL method based on Multi-hop feature Quality Estimation (MQE)
  arXiv  Detail & Related papers  (2024-07-29T12:24:28Z)
• Fair Graph Neural Network with Supervised Contrastive Regularization [12.666235467177131]
  We propose a novel model for training fairness-aware Graph Neural Networks (GNNs) Our approach integrates Supervised Contrastive Loss and Environmental Loss to enhance both accuracy and fairness.
  arXiv  Detail & Related papers  (2024-04-09T07:49:05Z)
• Endowing Pre-trained Graph Models with Provable Fairness [49.8431177748876]
  We propose a novel adapter-tuning framework that endows pre-trained graph models with provable fairness (called GraphPAR) Specifically, we design a sensitive semantic augmenter on node representations, to extend the node representations with different sensitive attribute semantics for each node. With GraphPAR, we quantify whether the fairness of each node is provable, i.e., predictions are always fair within a certain range of sensitive attribute semantics.
  arXiv  Detail & Related papers  (2024-02-19T14:16:08Z)
• FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently [29.457338893912656]
  Societal biases against sensitive groups may exist in many real world graphs. We present an in-depth analysis on how graph structure bias, node attribute bias, and model parameters may affect the demographic parity of GCNs. Our insights lead to FairSample, a framework that jointly mitigates the three types of biases.
  arXiv  Detail & Related papers  (2024-01-26T08:17:12Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• Fairness-Aware Graph Neural Networks: A Survey [53.41838868516936]
  Graph Neural Networks (GNNs) have become increasingly important due to their representational power and state-of-the-art predictive performance. GNNs suffer from fairness issues that arise as a result of the underlying graph data and the fundamental aggregation mechanism. In this article, we examine and categorize fairness techniques for improving the fairness of GNNs.
  arXiv  Detail & Related papers  (2023-07-08T08:09:06Z)
• Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage [35.810534649478576]
  Graph Neural Networks (GNNs) have shown great power in learning node representations on graphs. GNNs may inherit historical prejudices from training data, leading to discriminatory bias in predictions. We propose Fair View Graph Neural Network (FairVGNN) to generate fair views of features by automatically identifying and masking sensitive-correlated features.
  arXiv  Detail & Related papers  (2022-06-07T16:25:20Z)
• Fairness via Representation Neutralization [60.90373932844308]
  We propose a new mitigation technique, namely, Representation Neutralization for Fairness (RNF) RNF achieves that fairness by debiasing only the task-specific classification head of DNN models. Experimental results over several benchmark datasets demonstrate our RNF framework to effectively reduce discrimination of DNN models.
  arXiv  Detail & Related papers  (2021-06-23T22:26:29Z)

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.