Interpretable Data-Based Explanations for Fairness Debugging
Authors:
- Romila PradhanRPRomila Pradhan
- Jiongli ZhuJZJiongli Zhu
- Boris GlavicBGBoris Glavic
- Babak SalimiBSBabak Salimi
Preprint
Abstract
A wide variety of fairness metrics and eXplainable Artificial Intelligence (XAI) approaches have been proposed in the literature to identify bias in machine learning models that are used in critical real-life contexts. However, merely reporting on a model's bias, or generating explanations using existing XAI techniques is insufficient to locate and eventually mitigate sources of bias. We introduce Gopher, a system that produces compact, interpretable and causal explanations for bias or unexpected model behavior by identifying coherent subsets of the training data that are root-causes for this behavior. Specifically, we introduce the concept of causal responsibility that quantifies the extent to which intervening on training data by removing or updating subsets of it can resolve the bias. Building on this concept, we develop an efficient approach for generating the top-k patterns that explain model bias that utilizes techniques from the machine learning (ML) community to approximate causal responsibility and uses pruning rules to manage the large search space for patterns. Our experimental evaluation demonstrates the effectiveness of Gopher in generating interpretable explanations for identifying and debugging sources of bias.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Stronger data poisoning attacks break data sanitization defensesMachine Learning, 2021
- Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuesArtificial Intelligence, 2021
- Missing the missing values: The ugly duckling of fairness in machine learningInternational Journal of Intelligent Systems, 2021
- Poisoning Attacks on Algorithmic Fairness2021
- Automated Data Slicing for Model Validation: A Big Data - AI Integration ApproachIEEE Transactions on Knowledge and Data Engineering, 2019
- Transparent to whom? No algorithmic accountability without a critical audienceInformation, Communication & Society, 2018
- Fair, Transparent, and Accountable Algorithmic Decision-making ProcessesPhilosophy & Technology, 2017
- Certifying and Removing Disparate Impact2015
- Explaining prediction models and individual predictions with feature contributionsKnowledge and Information Systems, 2013
- Analysis of regression in game theory approachApplied Stochastic Models in Business and Industry, 2001