# On Baselines for Local Feature Attributions

arXiv: https://arxiv.org/abs/2101.00905 · HTML: https://mlsanity.com/paper/2101.00905/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 4 Jan 2021.

## Builds on (most cited first, 12 of 12)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Learning Parameter Distributions to Detect Concept Drift in Data Streams](https://mlsanity.com/paper/2010.09388/) (2020)
- [A Baseline for Shapley Values in MLPs: from Missingness to Neutrality](https://mlsanity.com/paper/2006.04896/) (2020)
- [Leveraging Model Inherent Variable Importance for Stable Online Feature Selection](https://mlsanity.com/paper/2006.10398/) (2020)

## Built on by (most cited first, 29 of 29)

- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [CRAFT: Concept Recursive Activation FacTorization for Explainability](https://mlsanity.com/paper/2211.10154/) (2022)
- [A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation](https://mlsanity.com/paper/2306.07304/) (2023)
- [A Consistent and Efficient Evaluation Strategy for Attribution Methods](https://mlsanity.com/paper/2202.00449/) (2022)
- [The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations](https://mlsanity.com/paper/2106.00786/) (2021)
- [Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis](https://mlsanity.com/paper/2202.07728/) (2022)
- [Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks](https://mlsanity.com/paper/2401.06654/) (2024)
- [Fast Hierarchical Games for Image Explanations](https://mlsanity.com/paper/2104.06164/) (2021)
- [Deletion and Insertion Tests in Regression Models](https://mlsanity.com/paper/2205.12423/) (2022)
- [BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence](https://mlsanity.com/paper/2207.05566/) (2022)
- [Change Detection for Local Explainability in Evolving Data Streams](https://mlsanity.com/paper/2209.02764/) (2022)
- [Dynamic Model Tree for Interpretable Data Stream Learning](https://mlsanity.com/paper/2203.16181/) (2022)
- [On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective](https://mlsanity.com/paper/2206.06854/) (2022)
- [The Disagreement Problem in Faithfulness Metrics](https://mlsanity.com/paper/2311.07763/) (2023)
- [Toward Understanding the Disagreement Problem in Neural Network Feature Attribution](https://mlsanity.com/paper/2404.11330/) (2024)
- [Standardized Evaluation of Machine Learning Methods for Evolving Data Streams](https://mlsanity.com/paper/2204.13625/) (2022)
- [Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights](https://mlsanity.com/paper/2208.06096/) (2022)
- [Fidelity-Aware Recommendation Explanations via Stochastic Path Integration](https://mlsanity.com/paper/2511.18047/) (2025)
- [A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines](https://mlsanity.com/paper/2111.07379/) (2021)
- [Fixing confirmation bias in feature attribution methods via semantic match](https://mlsanity.com/paper/2307.00897/) (2023)
- [Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations](https://mlsanity.com/paper/2409.17774/) (2024)
- [Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry](https://mlsanity.com/paper/2412.20798/) (2024)
- [Guidelines For The Choice Of The Baseline in XAI Attribution Methods](https://mlsanity.com/paper/2503.19813/) (2025)
- [Missingness Bias Calibration in Feature Attribution Explanations](https://mlsanity.com/paper/2603.04831/) (2026)
- [Root Causing Prediction Anomalies Using Explainable AI](https://mlsanity.com/paper/2403.02439/) (2024)
- [Choose Your Explanation: A Comparison of SHAP and GradCAM in Human Activity Recognition](https://mlsanity.com/paper/2412.16003/) (2024)
- [Saliency Methods are Encoders: Analysing Logical Relations Towards Interpretation](https://mlsanity.com/paper/2412.16204/) (2024)
- [Improving Adversarial Robustness of Attribution via Implicit Regularization](https://mlsanity.com/paper/2605.29983/) (2026)
- [XtrAIn: Training-Guided Occlusion for Feature Attribution](https://mlsanity.com/paper/2606.10877/) (2026)

## Abstract (arXiv)

High-performing predictive models, such as neural nets, usually operate as black boxes, which raises serious concerns about their interpretability. Local feature attribution methods help to explain black box models and are therefore a powerful tool for assessing the reliability and fairness of predictions. To this end, most attribution models compare the importance of input features with a reference value, often called baseline. Recent studies show that the baseline can heavily impact the quality of feature attributions. Yet, we frequently find simplistic baselines, such as the zero vector, in practice. In this paper, we show empirically that baselines can significantly alter the discriminative power of feature attributions. We conduct our analysis on tabular data sets, thus complementing recent works on image data. Besides, we propose a new taxonomy of baseline methods. Our experimental study illustrates the sensitivity of popular attribution models to the baseline, thus laying the foundation for a more in-depth discussion on sensible baseline methods for tabular data.