Are Your Reviewers Being Treated Equally? Discovering Subgroup Structures to Improve Fairness in Spam Detection
Not on the map. Why?
Abstract (arXiv)
User-generated reviews of products are vital assets of online commerce, such as Amazon and Yelp, while fake reviews are prevalent to mislead customers. GNN is the state-of-the-art method that detects suspicious reviewers by exploiting the topologies of the graph connecting reviewers, reviews, and target products. However, the discrepancy in the detection accuracy over different groups of reviewers can degrade reviewer engagement and customer trust in the review websites. Unlike the previous belief that the difference between the groups causes unfairness, we study the subgroup structures within the groups that can also cause discrepancies in treating different groups. This paper addresses the challenges of defining, approximating, and utilizing a new subgroup structure for fair spam detection. We first identify subgroup structures in the review graph that lead to discrepant accuracy in the groups. The complex dependencies over the review graph create difficulties in teasing out subgroups hidden within larger groups. We design a model that can be trained to jointly infer the hidden subgroup memberships and exploits the membership for calibrating the detection accuracy across groups. Comprehensive comparisons against baselines on three large Yelp review datasets demonstrate that the subgroup membership can be identified and exploited for group fairness.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 27 of its 46 references that are in the map. First posted on arXiv 24 Apr 2022.
Builds on
27 of 46 references.
References · 27
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,170
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,911
- 2016Equality of Opportunity in Supervised Learningcited by 2,005
- 2020Graph Contrastive Learning with Augmentationscited by 1,207
- 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
- 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 382
- 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
- 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
- 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
- 2020Data Augmentation for Graph Neural Networkscited by 203
- 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
15 more
- 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 150
- 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
- 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
- 2018Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobservedcited by 94
- 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
- 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
- 2021FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learningcited by 68
- 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 62
- 2019Spam Review Detection with Graph Convolutional Networkscited by 57
- 2020DeBayes: a Bayesian Method for Debiasing Network Embeddingscited by 55
- 2021Learning Fair Representations for Recommendation: A Graph-based Perspectivecited by 50
- 2019Equalized odds postprocessing under imperfect group informationcited by 48
- 2020Mitigating Bias in Set Selection with Noisy Protected Attributescited by 29
- 2020Robust Spammer Detection by Nash Reinforcement Learningcited by 17
- 2022FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editingcited by 15
Built on by
Not cited yet.