A new explanation method for ReLU neural networks that builds piecewise linear models from selected connected subsets of hidden units, called paths, to produce adjustable and decomposable input attributions.
Unwrapping All ReLU Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Deep ReLU Networks can be decomposed into a collection of linear models, each defined in a region of a partition of the input space. This paper provides three results extending this theory. First, we extend this linear decompositions to Graph Neural networks and tensor convolutional networks, as well as networks with multiplicative interactions. Second, we provide proofs that neural networks can be understood as interpretable models such as Multivariate Decision trees and logical theories. Finally, we show how this model leads to computing cheap and exact SHAP values. We validate the theory through experiments with on Graph Neural Networks.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pathwise Explanation of ReLU Neural Networks
A new explanation method for ReLU neural networks that builds piecewise linear models from selected connected subsets of hidden units, called paths, to produce adjustable and decomposable input attributions.