Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract)

Arjun Ashok, Chaitanya Devaguptapu, Vineeth N. Balasubramanian

AAAI 2022 pp. 12905-12906

doi:10.1609/AAAI.V36I11.21589 /aaai/2022/ashok2022aaai-learning/

Abstract

Out-of-distribution (O.O.D.) generalization remains to be a key challenge for real-world machine learning systems. We describe a method for O.O.D. generalization that, through training, encourages models to only preserve features in the network that are well reused across multiple training domains. Our method combines two complementary neuron-level regularizers with a probabilistic differentiable binary mask over the network, to extract a modular sub-network that achieves better O.O.D. performance than the original network. Preliminary evaluation on two benchmark datasets corroborates the promise of our method.

PDF AAAI Semantic Scholar

Cite

Text

Ashok et al. "Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21589

Markdown

[Ashok et al. "Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/ashok2022aaai-learning/) doi:10.1609/AAAI.V36I11.21589

BibTeX

@inproceedings{ashok2022aaai-learning,
  title     = {{Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract)}},
  author    = {Ashok, Arjun and Devaguptapu, Chaitanya and Balasubramanian, Vineeth N.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {12905-12906},
  doi       = {10.1609/AAAI.V36I11.21589},
  url       = {https://mlanthology.org/aaai/2022/ashok2022aaai-learning/}
}