Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract)
Keywords:Out Of Distribution Generalization, Modularity, Compositionality, Structure Learning, Systematic Generalization
AbstractOut-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.
How to Cite
Ashok, A., Devaguptapu, C., & Balasubramanian, V. N. (2022). Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12905-12906. https://doi.org/10.1609/aaai.v36i11.21589
AAAI Student Abstract and Poster Program