From f022b0c921734600a2fa5ccbeb06ddfcef844cd5 Mon Sep 17 00:00:00 2001 From: "Anh M. Nguyen" Date: Thu, 26 Aug 2021 16:30:04 -0500 Subject: [PATCH] Added Efficient Explanations from Empirical Explainers --- README.md | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index cc02aa2..1e89235 100644 --- a/README.md +++ b/README.md @@ -217,19 +217,22 @@ This is an on-going attempt to consolidate interesting efforts in the area of un * Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations. _Ross et al. IJCAI 2017_ [pdf](https://www.ijcai.org/Proceedings/2017/0371.pdf) * Learning Explainable Models Using Attribution Priors. _Erion et al. 2019_ [pdf](https://arxiv.org/abs/1906.10670) * Interpretations are useful: penalizing explanations to align neural networks with prior knowledge. _Rieger et al. 2019_ [pdf](https://arxiv.org/pdf/1909.13584.pdf) -* L2E: Learning to Explain: Generating Stable Explanations Fast. _Situ et al. ACL 2021_ [pdf](https://aclanthology.org/2021.acl-long.415.pdf "Training neural networks to mimic a black-box attribution methods e.g. Occlusion, LIME, SHAP produces a faster and more stable explanation method.") | [code](https://github.com/situsnow/L2E) -### B2.2 Explaining by examples (prototypes) +### B2.2 Training deep nets to approximate expensive, posthoc attribution methods +* L2E: Learning to Explain: Generating Stable Explanations Fast. _Situ et al. ACL 2021_ [pdf](https://aclanthology.org/2021.acl-long.415.pdf "Training neural networks to mimic a black-box attribution methods e.g. Occlusion, LIME, SHAP produces a faster and more stable explanation method.") | [code](https://github.com/situsnow/L2E) +* Efficient Explanations from Empirical Explainers. _Schwarzenberg et al. 2021_ [pdf](https://arxiv.org/abs/2103.15429 "Training deep nets to approximate Integrated Gradient and Shapley methods") + +### B2.3 Explaining by examples (prototypes) * This Looks Like That: Deep Learning for Interpretable Image Recognition. _Chen et al. NeurIPS 2019_ [pdf](https://arxiv.org/abs/1806.10574) | [code](https://github.com/cfchen-duke/ProtoPNet) * ProtoPNet: This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition. _Nauta et al. 2020_ [pdf](https://arxiv.org/pdf/2011.02863.pdf) * NP-ProtoPNet: These do not Look Like Those. _Singh et al. 2021_ [pdf](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9373404 "ProtoPNet with negative prototypes and applied to chest x-rays") -### B2.3 Adversarial attacks on XAI systems with humans in the loop +### B2.4 Adversarial attacks on XAI systems with humans in the loop * When and How to Fool Explainable Models (and Humans) with Adversarial Examples. _Vadilo et al. 2021_ [pdf](https://arxiv.org/abs/2107.01943 "A framework of scenarios, assumptions, and humans in an XAI system under adversarial attacks") * The effectiveness of feature attribution methods and its correlation with automatic evaluation scores. _Nguyen, Kim, Nguyen 2021_ [pdf](http://anhnguyen.me/project/feature-attribution-effectiveness/ "On image classification, feature attribution maps are less effective in improving human-AI team compared to a simple nearest-neighbor method. The effectiveness of heatmaps also does not correlate with their localization performance.") -### B2.4 Others +### B2.5 Others * Learning how to explain neural networks: PatternNet and PatternAttribution [pdf](https://arxiv.org/abs/1705.05598) * Deep Learning for Case-Based Reasoning through Prototypes [pdf](https://arxiv.org/pdf/1710.04806.pdf) * Unsupervised Learning of Neural Networks to Explain Neural Networks [pdf](https://arxiv.org/abs/1805.07468)