# Neural Network Attributions: A Causal Perspective

arXiv: https://arxiv.org/abs/1902.02302 · HTML: https://mlsanity.com/paper/1902.02302/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2019.

## Built on by (most cited first, 30 of 77)

- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Generative Causal Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.06643/) (2021)
- [Inducing Causal Structure for Interpretable Neural Networks](https://mlsanity.com/paper/2112.00826/) (2021)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Leveraging Explanations in Interactive Machine Learning: An Overview](https://mlsanity.com/paper/2207.14526/) (2022)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [A Causal Lens for Controllable Text Generation](https://mlsanity.com/paper/2201.09119/) (2022)
- [Rigorously Assessing Natural Language Explanations of Neurons](https://mlsanity.com/paper/2309.10312/) (2023)
- [Defining and Quantifying the Emergence of Sparse Concepts in DNNs](https://mlsanity.com/paper/2111.06206/) (2021)
- [Reinforced Causal Explainer for Graph Neural Networks](https://mlsanity.com/paper/2204.11028/) (2022)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning](https://mlsanity.com/paper/2405.16507/) (2024)
- [Variational Information Pursuit for Interpretable Predictions](https://mlsanity.com/paper/2302.02876/) (2023)
- [On Causally Disentangled Representations](https://mlsanity.com/paper/2112.05746/) (2021)
- [Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms](https://mlsanity.com/paper/2106.00925/) (2021)
- [Adaptive Fairness Improvement Based on Causality Analysis](https://mlsanity.com/paper/2209.07190/) (2022)
- [Interpretation of Time-Series Deep Models: A Survey](https://mlsanity.com/paper/2305.14582/) (2023)
- [Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations](https://mlsanity.com/paper/2504.12691/) (2025)
- [CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution](https://mlsanity.com/paper/2602.07918/) (2026)
- [LLMScan: Causal Scan for LLM Misbehavior Detection](https://mlsanity.com/paper/2410.16638/) (2024)
- [On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach](https://mlsanity.com/paper/2212.07056/) (2022)
- [Causality Analysis for Evaluating the Security of Large Language Models](https://mlsanity.com/paper/2312.07876/) (2023)
- [Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?](https://mlsanity.com/paper/2105.10719/) (2021)
- [Matching Learned Causal Effects of Neural Networks with Domain Priors](https://mlsanity.com/paper/2111.12490/) (2021)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction](https://mlsanity.com/paper/2312.16113/) (2023)
- [Instance-wise Causal Feature Selection for Model Interpretation](https://mlsanity.com/paper/2104.12759/) (2021)
- [Detecting Multi-Sensor Fusion Errors in Advanced Driver-Assistance Systems](https://mlsanity.com/paper/2109.06404/) (2021)

## Abstract (arXiv)

We propose a new attribution method for neural networks developed using first principles of causality (to the best of our knowledge, the first such). The neural network architecture is viewed as a Structural Causal Model, and a methodology to compute the causal effect of each feature on the output is presented. With reasonable assumptions on the causal structure of the input data, we propose algorithms to efficiently compute the causal effects, as well as scale the approach to data with large dimensionality. We also show how this method can be used for recurrent neural networks. We report experimental results on both simulated and real datasets showcasing the promise and usefulness of the proposed algorithm.