# A Unified Taylor Framework for Revisiting Attribution Methods

arXiv: https://arxiv.org/abs/2008.09695 · HTML: https://mlsanity.com/paper/2008.09695/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2020.

## Built on by (most cited first, 13 of 13)

- [Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models](https://mlsanity.com/paper/2103.06922/) (2021)
- [PredDiff: Explanations and Interactions from Conditional Expectations](https://mlsanity.com/paper/2102.13519/) (2021)
- [Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs](https://mlsanity.com/paper/2304.13312/) (2023)
- [Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions](https://mlsanity.com/paper/2303.01506/) (2023)
- [Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models](https://mlsanity.com/paper/2409.17455/) (2024)
- [Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attribution](https://mlsanity.com/paper/2308.04708/) (2023)
- [Interpretable Machine Learning for Weather and Climate Prediction: A Survey](https://mlsanity.com/paper/2403.18864/) (2024)
- [Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution](https://mlsanity.com/paper/2104.06629/) (2021)
- [Causal-discovery-based root-cause analysis and its application in time-series prediction error diagnosis](https://mlsanity.com/paper/2411.06990/) (2024)
- [Attribution Explanations for Deep Neural Networks: A Theoretical Perspective](https://mlsanity.com/paper/2508.07636/) (2025)
- [Black-Box Anomaly Attribution](https://mlsanity.com/paper/2305.18440/) (2023)
- [Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective](https://mlsanity.com/paper/2503.11160/) (2025)
- [GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification](https://mlsanity.com/paper/2608.05608/) (2026)

## Abstract (arXiv)

Attribution methods have been developed to understand the decision-making process of machine learning models, especially deep neural networks, by assigning importance scores to individual features. Existing attribution methods often built upon empirical intuitions and heuristics. There still lacks a general and theoretical framework that not only can unify these attribution methods, but also theoretically reveal their rationales, fidelity, and limitations. To bridge the gap, in this paper, we propose a Taylor attribution framework and reformulate seven mainstream attribution methods into the framework. Based on reformulations, we analyze the attribution methods in terms of rationale, fidelity, and limitation. Moreover, We establish three principles for a good attribution in the Taylor attribution framework, i.e., low approximation error, correct contribution assignment, and unbiased baseline selection. Finally, we empirically validate the Taylor reformulations and reveal a positive correlation between the attribution performance and the number of principles followed by the attribution method via benchmarking on real-world datasets.