# Finding Interpretable Class-Specific Patterns through Efficient Neural Search

arXiv: https://arxiv.org/abs/2312.04311 · HTML: https://mlsanity.com/paper/2312.04311/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 7 Dec 2023.

## Builds on (most cited first, 19 of 19)

- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm](https://mlsanity.com/paper/1808.00278/) (2018)
- [Generalized and Scalable Optimal Sparse Decision Trees](https://mlsanity.com/paper/2006.08690/) (2020)
- [Boolean Decision Rules via Column Generation](https://mlsanity.com/paper/1805.09901/) (2018)
- [ProxQuant: Quantized Neural Networks via Proximal Operators](https://mlsanity.com/paper/1810.00861/) (2018)
- [Scalable Rule-Based Representation Learning for Interpretable Classification](https://mlsanity.com/paper/2109.15103/) (2021)
- [Fast Sparse Decision Tree Optimization via Reference Ensembles](https://mlsanity.com/paper/2112.00798/) (2021)
- [Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)](https://mlsanity.com/paper/1807.06964/) (2018)
- [Transparent Classification with Multilayer Logical Perceptrons and Random Binarization](https://mlsanity.com/paper/1912.04695/) (2019)
- [Interpretable multiclass classification by MDL-based rule lists](https://mlsanity.com/paper/1905.00328/) (2019)
- [An Optimization Approach to Learning Falling Rule Lists](https://mlsanity.com/paper/1710.02572/) (2017)
- [Label-Descriptive Patterns and Their Application to Characterizing Classification Errors](https://mlsanity.com/paper/2110.09599/) (2021)
- [Fast and Memory-Efficient Significant Pattern Mining via Permutation Testing](https://mlsanity.com/paper/1502.04315/) (2015)
- [Differentiable Rule Induction with Learned Relational Features](https://mlsanity.com/paper/2201.06515/) (2022)
- [Efficient learning of large sets of locally optimal classification rules](https://mlsanity.com/paper/2301.09936/) (2023)
- [C-SALT: Mining Class-Specific ALTerations in Boolean Matrix Factorization](https://mlsanity.com/paper/1906.09907/) (2019)
- [Efficiently Factorizing Boolean Matrices using Proximal Gradient Descent](https://mlsanity.com/paper/2307.07615/) (2023)
- [Conformal Rule-Based Multi-label Classification](https://mlsanity.com/paper/2007.08145/) (2020)

## Built on by (most cited first, 5 of 5)

- [Learning Exceptional Subgroups by End-to-End Maximizing KL-divergence](https://mlsanity.com/paper/2402.12930/) (2024)
- [Compact Rule-Based Classifier Learning via Gradient Descent](https://mlsanity.com/paper/2502.01375/) (2025)
- [Differentiable Rule Induction from Raw Sequence Inputs](https://mlsanity.com/paper/2602.13583/) (2026)
- [Neuro-Symbolic Rule Lists](https://mlsanity.com/paper/2411.06428/) (2024)
- [Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data](https://mlsanity.com/paper/2609.03878/) (2026)

## Abstract (arXiv)

Discovering patterns in data that best describe the differences between classes allows to hypothesize and reason about class-specific mechanisms. In molecular biology, for example, this bears promise of advancing the understanding of cellular processes differing between tissues or diseases, which could lead to novel treatments. To be useful in practice, methods that tackle the problem of finding such differential patterns have to be readily interpretable by domain experts, and scalable to the extremely high-dimensional data. In this work, we propose a novel, inherently interpretable binary neural network architecture DIFFNAPS that extracts differential patterns from data. DiffNaps is scalable to hundreds of thousands of features and robust to noise, thus overcoming the limitations of current state-of-the-art methods in large-scale applications such as in biology. We show on synthetic and real world data, including three biological applications, that, unlike its competitors, DiffNaps consistently yields accurate, succinct, and interpretable class descriptions