Saliency Map-Guided Knowledge Discovery for Subclass Identification with LLM-Based Symbolic Approximations

TL;DR

This paper introduces a neuro-symbolic method that uses saliency maps from neural networks to identify latent subclasses in time series data, enhancing knowledge discovery and classification accuracy.

Contribution

It presents a novel approach combining saliency maps, clustering, and large language models for subclass discovery in time series classification tasks.

Findings

Outperforms baseline methods in subclass identification

Effective in clustering time series signals by class

Leverages LLMs for symbolic approximation and knowledge graph matching

Abstract

This paper proposes a novel neuro-symbolic approach for sensor signal-based knowledge discovery, focusing on identifying latent subclasses in time series classification tasks. The approach leverages gradient-based saliency maps derived from trained neural networks to guide the discovery process. Multiclass time series classification problems are transformed into binary classification problems through label subsumption, and classifiers are trained for each of these to yield saliency maps. The input signals, grouped by predicted class, are clustered under three distinct configurations. The centroids of the final set of clusters are provided as input to an LLM for symbolic approximation and fuzzy knowledge graph matching to discover the underlying subclasses of the original multiclass problem. Experimental results on well-established time series classification datasets demonstrate the effectiveness of our saliency map-driven method for knowledge discovery, outperforming signal-only baselines in both clustering and subclass identification.