Back to papers
Interpretable Data-Based Explanations for Fairness Debugging
Summary: Gopher yields compact data explanations for model bias by pinpointing training-subset root-causes. It defines causal responsibility and uses pruned-pattern mining with ML-based approximation to enable interventions for fairness debugging.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 6339
- Venue
- SIGMOD
- Year
- 2022
- Pagerank
- 0.00010263235
- Overall Rank
- 1,869 | 87.02%
- DOI
-
10.1145/3514221.3517886
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 16 of 16 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
| 2,987 |
NL2SQL is a solved problem... Not! |
2024 |
CIDR |
7.77529e-05 |
| 6,156 |
On Data-Aware Global Explainability of Graph Neural Networks |
2023 |
VLDB |
5.1779507e-05 |
| 6,999 |
Generating Interpretable Data-Based Explanations for Fairness Debugging using Gopher |
2022 |
SIGMOD |
4.8629617e-05 |
| 7,024 |
A Unified Approach for Resilience and Causal Responsibility with Integer Linear Programming (ILP) and LP Relaxations |
2023 |
SIGMOD |
4.8530001e-05 |
| 8,253 |
Automating and Optimizing Data-Centric What-If Analyses on Native Machine Learning Pipelines |
2023 |
SIGMOD |
4.5444167e-05 |
| 9,044 |
Efficient Approximation of Certain and Possible Answers for Ranking and Window Queries over Uncertain Data |
2023 |
VLDB |
4.3997447e-05 |
| 9,406 |
Explaining GNN-based Recommendations in Logic |
2025 |
VLDB |
4.3399748e-05 |
| 9,644 |
Fair and Actionable Causal Prescription Ruleset |
2025 |
SIGMOD |
4.3067693e-05 |
| 10,488 |
Data Enhancement for Binary Classification of Relational Data |
2025 |
SIGMOD |
4.1905499e-05 |
| 10,533 |
Understanding the Black Box: A Deep Empirical Dive into Shapley Value Approximations for Tabular Data |
2025 |
SIGMOD |
4.1905499e-05 |
| 10,747 |
Finding Convincing Views to Endorse a Claim |
2025 |
VLDB |
4.1905499e-05 |
| 10,764 |
Stress-Testing ML Pipelines with Adversarial Data Corruption |
2025 |
VLDB |
4.1905499e-05 |
| 10,821 |
mlidea: Interactively Improving ML Data Preparation Code via "Shadow Pipelines" |
2025 |
VLDB |
4.1905499e-05 |
| 10,957 |
Counterfactual Explanation at Will, with Zero Privacy Leakage |
2024 |
SIGMOD |
4.1905499e-05 |
| 11,003 |
MisDetect: Iterative Mislabel Detection using Early Loss |
2024 |
VLDB |
4.1905499e-05 |
| 11,150 |
Reconstructing and Querying ML Pipeline Intermediates |
2023 |
CIDR |
4.1905499e-05 |
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 182 |
Mining Frequent Patterns without Candidate Generation |
2000 |
SIGMOD |
0.00036955562 |
| 1,037 |
Interventional Fairness : Causal Database Repair for Algorithmic Fairness |
2019 |
SIGMOD |
0.00014514825 |
| 1,406 |
Responsible Data Management |
2020 |
VLDB |
0.0001216385 |
| 1,942 |
SliceLine: Fast, Linear-Algebra-based Slice Finding for ML Model Debugging |
2021 |
SIGMOD |
0.00010010569 |
| 2,759 |
Complaint-driven Training Data Debugging for Query 2.0 |
2020 |
SIGMOD |
8.1646193e-05 |
| 2,816 |
Bias in OLAP Queries: Detection, Explanation, and Removal (Or Think Twice About Your AVG-Query) |
2018 |
SIGMOD |
8.0747683e-05 |
| 3,807 |
HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning |
2021 |
SIGMOD |
6.7428898e-05 |
| 4,423 |
PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models |
2020 |
SIGMOD |
6.1925724e-05 |
| 4,731 |
MLINSPECT: A Data Distribution Debugger for Machine Learning Pipelines |
2021 |
SIGMOD |
5.9558692e-05 |
| 6,895 |
Identifying Insufficient Data Coverage for Ordinal Continuous-Valued Attributes |
2021 |
SIGMOD |
4.8879337e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 7,853 |
Consistent Range Approximation for Fair Predictive Modeling |
2023 |
VLDB |
4.6308623e-05 |
| 6,565 |
Toward Interpretable and Actionable Data Analysis with Explanations and Causality |
2022 |
VLDB |
5.0033542e-05 |
| 9,644 |
Fair and Actionable Causal Prescription Ruleset |
2025 |
SIGMOD |
4.3067693e-05 |
| 11,150 |
Reconstructing and Querying ML Pipeline Intermediates |
2023 |
CIDR |
4.1905499e-05 |
| 2,925 |
Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals |
2021 |
SIGMOD |
7.8877522e-05 |
| 10,438 |
CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets |
2025 |
SIGMOD |
4.1905499e-05 |
| 4,761 |
Automated Feature Engineering for Algorithmic Fairness |
2021 |
VLDB |
5.9341687e-05 |
| 7,605 |
Causal Feature Selection for Algorithmic Fairness |
2022 |
SIGMOD |
4.6943015e-05 |
| 1,037 |
Interventional Fairness : Causal Database Repair for Algorithmic Fairness |
2019 |
SIGMOD |
0.00014514825 |
| 6,999 |
Generating Interpretable Data-Based Explanations for Fairness Debugging using Gopher |
2022 |
SIGMOD |
4.8629617e-05 |