Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights
Not on the map. Why?
Abstract (arXiv)
There are many different methods in the literature for local explanation of machine learning results. However, the methods differ in their approaches and often do not provide same explanations. In this paper, we consider two recent methods: Integrated Gradients (Sundararajan, Taly, & Yan, 2017) and Baseline Shapley (Sundararajan and Najmi, 2020). The original authors have already studied the axiomatic properties of the two methods and provided some comparisons. Our work provides some additional insights on their comparative behavior for tabular data. We discuss common situations where the two provide identical explanations and where they differ. We also use simulation studies to examine the differences when neural networks with ReLU activation function is used to fit the models.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 48 of its 68 references that are in the map. First posted on arXiv 12 Aug 2022.
Builds on
48 of 68 references.
References · 48
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2018Sanity Checks for Saliency Mapscited by 1,156
- 2017SmoothGrad: removing noise by adding noisecited by 1,109
- 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
- 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
- 2017Interpretation of Neural Networks is Fragilecited by 444
- 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
- 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 344
36 more
- 2019The many Shapley values for model explanationcited by 344
- 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
- 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 297
- 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 285
- 2019Explanations can be manipulated and geometry is to blamecited by 216
- 2020Evaluating and Aggregating Feature-based Model Explanationscited by 188
- 2019Feature relevance quantification in explainable AI: A causal problemcited by 167
- 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
- 2020True to the Model or True to the Data?cited by 126
- 2019XRAI: Better Attributions Through Regionscited by 116
- 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
- 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
- 2019Fooling Neural Network Interpretations via Adversarial Model Manipulationcited by 112
- 2020Explaining Explanations: Axiomatic Feature Interactions for Deep Networkscited by 103
- 2021Guided Integrated Gradients: An Adaptive Path Method for Removing Noisecited by 102
- 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
- 2018How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanationcited by 72
- 2019Explainable AI for Trees: From Local Explanations to Global Understandingcited by 65
- 2022A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributionscited by 64
- 2020Attribution in Scale and Spacecited by 61
- 2020Shapley Flow: A Graph-based Approach to Interpreting Model Predictionscited by 51
- 2021Discretized Integrated Gradients for Explaining Language Modelscited by 46
- 2020Gradient-based Analysis of NLP Models is Manipulablecited by 41
- 2014Effective Use of Word Order for Text Categorization with Convolutional Neural Networkscited by 40
- 2019Improving performance of deep learning models with axiomatic attribution priors and expected gradientscited by 32
- 2020Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplificationcited by 32
- 2019Explaining Models by Propagating Shapley Values of Local Componentscited by 29
- 2021On Baselines for Local Feature Attributionscited by 29
- 2016An unexpected unity among methods for interpreting model predictionscited by 17
- 2021Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospitalcited by 17
- 2020A Baseline for Shapley Values in MLPs: from Missingness to Neutralitycited by 11
- 2018A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Valuescited by 9
- 2019Generalized Integrated Gradients: A practical method for explaining diverse ensemblescited by 7
- 2020Supervised Machine Learning Techniques: An Overview with Applications to Bankingcited by 7
- 2022Explaining Adverse Actions in Credit Decisions Using Shapley Decompositioncited by 4
- 2020Adversarial Attacks and Defenses: An Interpretation Perspectivecited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 2.
3 papers.