# CGXplain: Rule-Based Deep Neural Network Explanations Using Dual Linear Programs

arXiv: https://arxiv.org/abs/2304.05207 · HTML: https://mlsanity.com/paper/2304.05207/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 5 of 5)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Boolean Decision Rules via Column Generation](https://mlsanity.com/paper/1805.09901/) (2018)
- [Explainable Artificial Intelligence Approaches: A Survey](https://mlsanity.com/paper/2101.09429/) (2021)
- [Efficient Decompositional Rule Extraction for Deep Neural Networks](https://mlsanity.com/paper/2111.12628/) (2021)

## Built on by (most cited first, 3 of 3)

- [NEUROLOGIC: From Neural Representations to Interpretable Logic Rules](https://mlsanity.com/paper/2501.08281/) (2025)
- [ADLGen: Synthesizing Symbolic, Event-Triggered Sensor Sequences for Human Activity Modeling](https://mlsanity.com/paper/2505.17987/) (2025)
- [Textual Explanations and Their Evaluations for Reinforcement Learning Policy](https://mlsanity.com/paper/2601.02514/) (2026)

## Abstract (arXiv)

Rule-based surrogate models are an effective and interpretable way to approximate a Deep Neural Network's (DNN) decision boundaries, allowing humans to easily understand deep learning models. Current state-of-the-art decompositional methods, which are those that consider the DNN's latent space to extract more exact rule sets, manage to derive rule sets at high accuracy. However, they a) do not guarantee that the surrogate model has learned from the same variables as the DNN (alignment), b) only allow to optimise for a single objective, such as accuracy, which can result in excessively large rule sets (complexity), and c) use decision tree algorithms as intermediate models, which can result in different explanations for the same DNN (stability). This paper introduces the CGX (Column Generation eXplainer) to address these limitations - a decompositional method using dual linear programming to extract rules from the hidden representations of the DNN. This approach allows to optimise for any number of objectives and empowers users to tweak the explanation model to their needs. We evaluate our results on a wide variety of tasks and show that CGX meets all three criteria, by having exact reproducibility of the explanation model that guarantees stability and reduces the rule set size by >80% (complexity) at equivalent or improved accuracy and fidelity across tasks (alignment).