Related papers: Marginal Nodes Matter: Towards Structure Fairness in Graphs

Marginal Nodes Matter: Towards Structure Fairness in Graphs

URL: http://arxiv.org/abs/2310.14527v1
Date: Mon, 23 Oct 2023 03:20:32 GMT
Title: Marginal Nodes Matter: Towards Structure Fairness in Graphs
Authors: Xiaotian Han, Kaixiong Zhou, Ting-Hsiang Wang, Jundong Li, Fei Wang, Na Zou
Abstract summary: We propose textbfStructural textbfFair textbfGraph textbfNeural textbfNetwork (SFairGNN) to achieve structure fairness. Our experiments show SFairGNN can significantly improve structure fairness while maintaining overall performance in the downstream tasks.
Score: 77.25149739933596
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protecting sensitive attributes (e.g., age and gender), the fairness incurred by the graph structure should also be given attention. On the other hand, the information aggregation mechanism of graph neural networks amplifies such structure unfairness, as marginal nodes are often far away from other nodes. In this paper, we focus on novel fairness incurred by the graph structure on graph neural networks, named \emph{structure fairness}. Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks. Motivated by the observation, we propose \textbf{S}tructural \textbf{Fair} \textbf{G}raph \textbf{N}eural \textbf{N}etwork (SFairGNN), which combines neighborhood expansion based structure debiasing with hop-aware attentive information aggregation to achieve structure fairness. Our experiments show \SFairGNN can significantly improve structure fairness while maintaining overall performance in the downstream tasks.

Related papers

Federated Graph Semantic and Structural Learning [54.97668931176513]
This paper reveals that local client distortion is brought by both node-level semantics and graph-level structure. We postulate that a well-structural graph neural network possesses similarity for neighbors due to the inherent adjacency relationships. We transform the adjacency relationships into the similarity distribution and leverage the global model to distill the relation knowledge into the local model.
arXiv Detail & Related papers (2024-06-27T07:08:28Z)
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)
Self-attention Dual Embedding for Graphs with Heterophily [6.803108335002346]
A number of real-world graphs are heterophilic, and this leads to much lower classification accuracy using standard GNNs. We design a novel GNN which is effective for both heterophilic and homophilic graphs. We evaluate our algorithm on real-world graphs containing thousands to millions of nodes and show that we achieve state-of-the-art results.
arXiv Detail & Related papers (2023-05-28T09:38:28Z)
CAFIN: Centrality Aware Fairness inducing IN-processing for Unsupervised Representation Learning on Graphs [10.042608422528392]
We propose CAFIN, a centrality-aware fairness-inducing framework to tune the representations generated by existing frameworks. We deploy it on GraphSAGE and showcase its efficacy on two downstream tasks - Node Classification and Link Prediction.
arXiv Detail & Related papers (2023-04-10T05:40:09Z)
Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions [51.597480162777074]
Graph neural networks (GNNs) rely on the message passing paradigm to propagate node features and build interactions. Recent works point out that different graph learning tasks require different ranges of interactions between nodes. We study two common graph construction methods in scientific domains, i.e., emphK-nearest neighbor (KNN) graphs and emphfully-connected (FC) graphs.
arXiv Detail & Related papers (2022-05-15T11:38:14Z)
Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical [85.0376670244522]
We investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. We develop a Star-shaped Reasoning Graph Network (S-RGN) to exploit more powerful and flexible capacity. We also develop a Hierarchical Reasoning Graph Network (H-RGN) to exploit more powerful and flexible capacity.
arXiv Detail & Related papers (2021-09-06T03:16:56Z)
Spectral Embedding of Graph Networks [76.27138343125985]
We introduce an unsupervised graph embedding that trades off local node similarity and connectivity, and global structure. The embedding is based on a generalized graph Laplacian, whose eigenvectors compactly capture both network structure and neighborhood proximity in a single representation.
arXiv Detail & Related papers (2020-09-30T04:59:10Z)

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