# Adversarial Infidelity Learning for Model Interpretation

arXiv: https://arxiv.org/abs/2006.05379 · HTML: https://mlsanity.com/paper/2006.05379/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Reinforced Causal Explainer for Graph Neural Networks](https://mlsanity.com/paper/2204.11028/) (2022)
- [Contrastive Video Question Answering via Video Graph Transformer](https://mlsanity.com/paper/2302.13668/) (2023)
- [DEGREE: Decomposition Based Explanation For Graph Neural Networks](https://mlsanity.com/paper/2305.12895/) (2023)
- [Self-explaining deep models with logic rule reasoning](https://mlsanity.com/paper/2210.07024/) (2022)
- [Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives](https://mlsanity.com/paper/2111.04898/) (2021)
- [On Pitfalls of textitRemOve-And-Retrain: Data Processing Inequality Perspective](https://mlsanity.com/paper/2304.13836/) (2023)
- [Towards interpreting ML-based automated malware detection models: a survey](https://mlsanity.com/paper/2101.06232/) (2021)
- [Towards Explanation for Unsupervised Graph-Level Representation Learning](https://mlsanity.com/paper/2205.09934/) (2022)

## Abstract (arXiv)

Model interpretation is essential in data mining and knowledge discovery. It can help understand the intrinsic model working mechanism and check if the model has undesired characteristics. A popular way of performing model interpretation is Instance-wise Feature Selection (IFS), which provides an importance score of each feature representing the data samples to explain how the model generates the specific output. In this paper, we propose a Model-agnostic Effective Efficient Direct (MEED) IFS framework for model interpretation, mitigating concerns about sanity, combinatorial shortcuts, model identifiability, and information transmission. Also, we focus on the following setting: using selected features to directly predict the output of the given model, which serves as a primary evaluation metric for model-interpretation methods. Apart from the features, we involve the output of the given model as an additional input to learn an explainer based on more accurate information. To learn the explainer, besides fidelity, we propose an Adversarial Infidelity Learning (AIL) mechanism to boost the explanation learning by screening relatively unimportant features. Through theoretical and experimental analysis, we show that our AIL mechanism can help learn the desired conditional distribution between selected features and targets. Moreover, we extend our framework by integrating efficient interpretation methods as proper priors to provide a warm start. Comprehensive empirical evaluation results are provided by quantitative metrics and human evaluation to demonstrate the effectiveness and superiority of our proposed method. Our code is publicly available online at https://github.com/langlrsw/MEED.