# RuDi: Explaining Behavior Sequence Models by Automatic Statistics Generation and Rule Distillation

arXiv: https://arxiv.org/abs/2208.07211 · HTML: https://mlsanity.com/paper/2208.07211/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 12 Aug 2022.

## Builds on (most cited first, 17 of 17)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [Harnessing Deep Neural Networks with Logic Rules](https://mlsanity.com/paper/1603.06318/) (2016)
- [Scalable Bayesian Rule Lists](https://mlsanity.com/paper/1602.08610/) (2016)
- [Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation](https://mlsanity.com/paper/1710.06169/) (2017)
- [Scalable Rule-Based Representation Learning for Interpretable Classification](https://mlsanity.com/paper/2109.15103/) (2021)
- [Improving the Interpretability of Deep Neural Networks with Knowledge Distillation](https://mlsanity.com/paper/1812.10924/) (2018)
- [One button machine for automating feature engineering in relational databases](https://mlsanity.com/paper/1706.00327/) (2017)
- [Learning Algorithms via Neural Logic Networks](https://mlsanity.com/paper/1904.01554/) (2019)
- [Transparent Classification with Multilayer Logical Perceptrons and Random Binarization](https://mlsanity.com/paper/1912.04695/) (2019)
- [Distilling Knowledge from Deep Networks with Applications to Healthcare Domain](https://mlsanity.com/paper/1512.03542/) (2015)
- [DIFER: Differentiable Automated Feature Engineering](https://mlsanity.com/paper/2010.08784/) (2020)
- [VEWS: A Wikipedia Vandal Early Warning System](https://mlsanity.com/paper/1507.01272/) (2015)
- [Causality-based Feature Selection: Methods and Evaluations](https://mlsanity.com/paper/1911.07147/) (2019)
- [Insider Threat Detection via Hierarchical Neural Temporal Point Processes](https://mlsanity.com/paper/1910.03171/) (2019)

## Built on by (most cited first, 1 of 1)

- [CohortNet: Empowering Cohort Discovery for Interpretable Healthcare Analytics](https://mlsanity.com/paper/2406.14015/) (2024)

## Abstract (arXiv)

Risk scoring systems have been widely deployed in many applications, which assign risk scores to users according to their behavior sequences. Though many deep learning methods with sophisticated designs have achieved promising results, the black-box nature hinders their applications due to fairness, explainability, and compliance consideration. Rule-based systems are considered reliable in these sensitive scenarios. However, building a rule system is labor-intensive. Experts need to find informative statistics from user behavior sequences, design rules based on statistics and assign weights to each rule. In this paper, we bridge the gap between effective but black-box models and transparent rule models. We propose a two-stage method, RuDi, that distills the knowledge of black-box teacher models into rule-based student models. We design a Monte Carlo tree search-based statistics generation method that can provide a set of informative statistics in the first stage. Then statistics are composed into logical rules with our proposed neural logical networks by mimicking the outputs of teacher models. We evaluate RuDi on three real-world public datasets and an industrial dataset to demonstrate its effectiveness.