Training Neural Networks for Modularity aids Interpretability

Satvik Golechha, Dylan Cope, Nandi SchootsWithdrawn

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models to be highly unclusterable and thus train models to be more modular using an ``enmeshment loss'' function that encourages the formation of non-interacting clusters. Using automated interpretability measures, we show that our method finds clusters that learn different, disjoint, and smaller circuits for CIFAR-10 labels. Our approach provides a promising direction for making neural networks easier to interpret.
BibTeX
@inproceedings{golechha2024training,
  author = {Satvik Golechha and Dylan Cope and Nandi Schoots},
  title = {{Training Neural Networks for Modularity aids Interpretability}},
  booktitle = {SciForDL @ NeurIPS},
  year = {2024},
  url = {https://openreview.net/forum?id=tCmP4OXesS},
}

Loading related content...

Figure