On Explaining Unfairness: An Overview
Not on the map. Why?
Abstract (arXiv)
Algorithmic fairness and explainability are foundational elements for achieving responsible AI. In this paper, we focus on their interplay, a research area that is recently receiving increasing attention. To this end, we first present two comprehensive taxonomies, each representing one of the two complementary fields of study: fairness and explanations. Then, we categorize explanations for fairness into three types: (a) Explanations to enhance fairness metrics, (b) Explanations to help us understand the causes of (un)fairness, and (c) Explanations to assist us in designing methods for mitigating unfairness. Finally, based on our fairness and explanation taxonomies, we present undiscovered literature paths revealing gaps that can serve as valuable insights for future research.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 51 of its 91 references that are in the map. First posted on arXiv 16 Feb 2024.
Builds on
51 of 91 references.
References · 51
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
- 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
- 2017Counterfactual Fairnesscited by 802
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
- 2020Fairness in Machine Learning: A Surveycited by 369
- 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
- 2018Actionable Recourse in Linear Classificationcited by 327
38 more
- 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
- 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
- 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
- 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
- 2021A survey on datasets for fairness-aware machine learningcited by 157
- 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
- 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
- 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
- 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
- 2021Towards Long-term Fairness in Recommendationcited by 77
- 2022Fairness in Graph Mining: A Surveycited by 76
- 2020Fairness-Aware Explainable Recommendation over Knowledge Graphscited by 74
- 2019Guarantees for Spectral Clustering with Fairness Constraintscited by 72
- 2020On the Fairness of Causal Algorithmic Recoursecited by 69
- 2019Operationalizing Individual Fairness with Pairwise Fair Representationscited by 64
- 2021Fairness in Rankings and Recommendations: An Overviewcited by 62
- 2022Learning Fair Node Representations with Graph Counterfactual Fairnesscited by 58
- 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
- 2019Equalizing Recourse across Groupscited by 51
- 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
- 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
- 2022FMP: Toward Fair Graph Message Passing against Topology Biascited by 35
- 2021CrossWalk: Fairness-enhanced Node Representation Learningcited by 34
- 2020Explainability for fair machine learningcited by 33
- 2021Fairness in Ranking: A Surveycited by 33
- 2020ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performancecited by 30
- 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
- 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
- 2023GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanationscited by 27
- 2022Fairness and Explainability: Bridging the Gap Towards Fair Model Explanationscited by 22
- 2022Interpreting Unfairness in Graph Neural Networks via Training Node Attributioncited by 18
- 2021The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizercited by 17
- 2021Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decompositioncited by 17
- 2022Explainable Fairness in Recommendationcited by 15
- 2022On Structural Explanation of Bias in Graph Neural Networkscited by 15
- 2023Counterfactual Explanation for Fairness in Recommendationcited by 9
- 2023Fairness Aware Counterfactuals for Subgroupscited by 8
- 2023GNNUERS: Fairness Explanation in GNNs for Recommendation via Counterfactual Reasoningcited by 7
50 most cited of 51 All 51 (JSON)
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.