A Repository to keep track of papers involving ML explainability particularly leveraging it for Model Debugging.
| Title | Author | Conf | Notes | Link |
|---|---|---|---|---|
| Debugging Tests for Model Explanations | Julius Adebayo, Michael Muelly, Ilaria Liccardi, Been Kim | NeurIPS 2020 | Using Post-Hoc Model Explanations to diagnose model errors | https://arxiv.org/pdf/2011.05429.pdf |
| Understanding Black-box Predictions via Influence Functions | Pang Wei Koh, Percy Liang | ICML 2017 | Identifying training points most responsible for a given prediction | https://arxiv.org/abs/1703.04730 |
| Characterizing and Detecting Mismatch in Machine-Learning-Enabled System | Grace A. Lewis, Stephany Bellomo, Ipek Ozkaya | WAIN 2021 | Collected and validated common types of mismatches that occur in end-to-end development of ML-enabled systems. | https://arxiv.org/pdf/2103.14101.pdf |
| Taxonomy of Real Faults in Deep Learning Systems | Nargiz Humbatova, Gunel Jahangirova, Gabriele Bavota, Vincenzo Riccio, Andrea Stocco, Paolo Tonella | ICSE 20 | Introduce a large taxonomy of faults in deep learning (DL) systems | https://arxiv.org/pdf/1910.11015.pdf |
| How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods | Jeya Vikranth Jeyakumar, Joseph Noor, Yu-Hsi Cheng, Luis Garcia, Mani Srivastava | NeurIPS 2020 | Comparing the popular state-of-the-art explanation methods to empirically determine which are better in explaining model decisions. | https://proceedings.neurips.cc/paper/2020/file/2c29d89cc56cdb191c60db2f0bae796b-Paper.pdf |
| On Calibration of Modern Neural Networks | JChuan Guo, Geoff Pleiss, Yu Sun, Kilian Q. Weinberger | ICML 2017 | Survey and Analysis of Model Calibration Methods | https://arxiv.org/pdf/1706.04599.pdf |
| Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges | Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, Chudi Zhong | Statistics Surveys, 2021 | Survey in Interpretability - Worth a read | https://arxiv.org/pdf/2103.11251.pdf |
| Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks | Haofan Wang , Zifan Wang , Mengnan Du , Fan Yang , Zijian Zhang , Sirui Ding , Piotr Mardziel , Xia Hu | CVPR 2020 | Uses Activation Maps as Masks. Improves over other CAM methods. | https://openaccess.thecvf.com/content_CVPRW_2020/papers/w1/Wang_Score-CAM_Score-Weighted_Visual_Explanations_for_Convolutional_Neural_Networks_CVPRW_2020_paper.pdf |