Compositionality Unlocks Deep Interpretable Models

We propose $\chi$-net, an intrinsically interpretable architecture combining the compositional multilinear structure of tensor networks with the expressivity and efficiency of deep neural networks. $\chi$-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.

@article{dooms2025_2504.02667,
  title={ Compositionality Unlocks Deep Interpretable Models },
  author={ Thomas Dooms and Ward Gauderis and Geraint A. Wiggins and Jose Oramas },
  journal={arXiv preprint arXiv:2504.02667},
  year={ 2025 }
}