Compositionality Unlocks Deep Interpretable Models

Thomas Dooms^*, Ward Gauderis^*, Geraint Wiggins, and 1 more author

In Connecting Low-Rank Representations in AI: At the 39th Annual AAAI Conference on Artificial Intelligence, Nov 2024

@inproceedings{doomsCompositionalityUnlocksDeep24,
  title = {Compositionality {Unlocks} {Deep} {Interpretable} {Models}},
  url = {https://openreview.net/forum?id=bXAt5iZ69l},
  urldate = {2025-02-17},
  booktitle = {Connecting {Low}-{Rank} {Representations} in {AI}: {At} the 39th {Annual} {AAAI} {Conference} on {Artificial} {Intelligence}},
  author = {Dooms, Thomas and Gauderis, Ward and Wiggins, Geraint and Mogrovejo, Jose Antonio Oramas},
  month = nov,
  year = {2024},
}

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 weightbased interpretability and model compression.