Finding Interpretable Class-Specific Patterns through Efficient Neural Search
This work addresses the need for scalable and interpretable methods to find differential patterns in high-dimensional data, particularly for domain experts in fields like biology, though it appears incremental as it builds on existing pattern-finding approaches.
The authors tackled the problem of discovering interpretable class-specific patterns in high-dimensional data, such as molecular biology, by proposing DiffNaps, a binary neural network architecture that consistently yields accurate and succinct descriptions on synthetic and real-world datasets, including three biological applications.
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