Synthetic Benchmarks for Scientific Research in Explainable Machine Learning
arXiv:2106.12543
Abstract
As machine learning models grow more complex and their applications become more high-stakes, tools for explaining model predictions have become increasingly important. This has spurred a flurry of research in model explainability and has given rise to feature attribution methods such as LIME and SHAP. Despite their widespread use, evaluating and comparing different feature attribution methods remains challenging: evaluations ideally require human studies, and empirical evaluation metrics are often data-intensive or computationally prohibitive on real-world datasets. In this work, we address this issue by releasing XAI-Bench: a suite of synthetic datasets along with a library for benchmarking feature attribution algorithms. Unlike real-world datasets, synthetic datasets allow the efficient computation of conditional expected values that are needed to evaluate ground-truth Shapley values and other metrics. The synthetic datasets we release offer a wide variety of parameters that can be configured to simulate real-world data. We demonstrate the power of our library by benchmarking popular explainability techniques across several evaluation metrics and across a variety of settings. The versatility and efficiency of our library will help researchers bring their explainability methods from development to deployment. Our code is available at https://github.com/abacusai/xai-bench.
arXiv commentNeurIPS Datasets and Benchmarks Track 2021
References in corpus (17)
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- This Looks Like That: Deep Learning for Interpretable Image Recognition
- Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
- Fairness in Machine Learning
- Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
- One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
- Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
- Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions
- Consistent feature attribution for tree ensembles
- Model Agnostic Supervised Local Explanations
- To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods
- Benchmarking Attribution Methods with Relative Feature Importance
- Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation
- True to the Model or True to the Data?
- Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
- A Survey on Neural Network Interpretability
- On quantitative aspects of model interpretability