Compositionality Unlocks Deep Interpretable Models
Thomas Dooms, Ward Gauderis, Geraint A. Wiggins, Jose Oramas
4/3/2025
cs.LG
No confident code implementation found for this paper.
Abstract
We propose $χ$-net, an intrinsically interpretable architecture combining the compositional multilinear structure of tensor networks with the expressivity and efficiency of deep neural networks. $χ$-nets retain equal accuracy compared to their baseline counterparts. Our novel, efficient diagonalisation algorithm, ODT, reveals linear low-rank structure in a multilayer SVHN model. We leverage this toward formal weight-based interpretability and model compression.
