# Towards Interaction Detection Using Topological Analysis on Neural Networks

arXiv: https://arxiv.org/abs/2010.13015 · HTML: https://mlsanity.com/paper/2010.13015/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2020.

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

- [Topological Detection of Trojaned Neural Networks](https://mlsanity.com/paper/2106.06469/) (2021)
- [Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model](https://mlsanity.com/paper/2305.15265/) (2023)
- [Editable Graph Neural Network for Node Classifications](https://mlsanity.com/paper/2305.15529/) (2023)
- [Addressing caveats of neural persistence with deep graph persistence](https://mlsanity.com/paper/2307.10865/) (2023)
- [DeepROCK: Error-controlled interaction detection in deep neural networks](https://mlsanity.com/paper/2309.15319/) (2023)

## Abstract (arXiv)

Detecting statistical interactions between input features is a crucial and challenging task. Recent advances demonstrate that it is possible to extract learned interactions from trained neural networks. It has also been observed that, in neural networks, any interacting features must follow a strongly weighted connection to common hidden units. Motivated by the observation, in this paper, we propose to investigate the interaction detection problem from a novel topological perspective by analyzing the connectivity in neural networks. Specially, we propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. Based on this measure, a Persistence Interaction detection~(PID) algorithm is developed to efficiently detect interactions. Our proposed algorithm is evaluated across a number of interaction detection tasks on several synthetic and real world datasets with different hyperparameters. Experimental results validate that the PID algorithm outperforms the state-of-the-art baselines.