Towards a fuller understanding of neurons with Clustered Compositional Explanations
Biagio La Rosa, Leilani H. Gilpin, Roberto Capobianco
Abstract
Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations (i.e., the highest ones) used to check the alignment, thus lacking completeness. In this paper, we propose a generalization, called Clustered Compositional Explanations, that combines Compositional Explanations with clustering and a novel search heuristic to approximate a broader spectrum of the neuron behavior. We define and address the problems connected to the application of these methods to multiple ranges of activations, analyze the insights retrievable by using our algorithm, and propose desiderata qualities that can be used to study the explanations returned by different algorithms.
BibTeX
@inproceedings{
rosa2023towards,
title={Towards a fuller understanding of neurons with Clustered Compositional Explanations},
author={Biagio La Rosa and Leilani H. Gilpin and Roberto Capobianco},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=51PLYhMFWz}
}