CISPA
Browse
28756-Article Text-32810-1-2-20240324.pdf (435.34 kB)

Finding Interpretable Class-Specific Patterns through Efficient Neural Search

Download (435.34 kB)
conference contribution
posted on 2024-04-17, 11:17 authored by Nils Philipp Walter, Jonas Fischer, Jilles VreekenJilles Vreeken
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, these bear the 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.

History

Editor

Wooldridge MJ ; Dy JG ; Natarajan S

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

National Conference of the American Association for Artificial Intelligence (AAAI)

Journal

Proceedings of the AAAI Conference on Artificial Intelligence

Volume

38

Page Range

9062-9070

Publisher

Association for the Advancement of Artificial Intelligence (AAAI)

Open Access Type

  • Gold

BibTeX

@inproceedings{Walter:Fischer:Vreeken:2024, title = "Finding Interpretable Class-Specific Patterns through Efficient Neural Search", author = "Walter, Nils Philipp" AND "Fischer, Jonas" AND "Vreeken, Jilles", editor = "Wooldridge, Michael J" AND "Dy, Jennifer G" AND "Natarajan, Sriraam", year = 2024, month = 3, journal = "Proceedings of the AAAI Conference on Artificial Intelligence", number = "8", pages = "9062--9070", publisher = "Association for the Advancement of Artificial Intelligence (AAAI)", issn = "2159-5399", doi = "10.1609/aaai.v38i8.28756" }