Publication

Memorize or generalize? Searching for a compositional RNN in a haystack

IJCAI-ECAI Workshop: Architectures and Evaluation for Generality, Autonomy & Progress in AI


Abstract

Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared by different tasks, and recombining them to solve new problems. In this paper, we explore the compositional generalization capabilities of recurrent neural networks (RNNs). We first propose the lookup table composition domain as a simple setup to test compositional behaviour and show that it is theoretically possible for a standard RNN to learn to behave compositionally in this domain when trained with standard gradient descent and provided with additional supervision. We then remove this additional supervision and perform a search over a large number of model initializations to investigate the proportion of RNNs that can still converge to a compositional solution. We discover that a small but non-negligible proportion of RNNs do reach partial compositional solutions even without special architectural constraints. This suggests that a combination of gradient descent and evolutionary strategies directly favouring the minority models that developed more compositional approaches might suffice to lead standard RNNs towards compositional solutions.

Related Publications

All Publications

COLING - December 8, 2020

Best Practices for Data-Efficient Modeling in NLG: How to Train Production-Ready Neural Models with Less Data

Ankit Arun, Soumya Batra, Vikas Bhardwaj, Ashwini Challa, Pinar Donmez, Peyman Heidari, Hakan Inan, Shashank Jain, Anuj Kumar, Shawn Mei, Karthik Mohan, Michael White

NeurIPS - December 1, 2020

Continuous Surface Embeddings

Natalia Neverova, David Novotny, Vasil Khalidov, Marc Szafraniec, Patrick Labatut, Andrea Vedaldi

NeurIPS - November 25, 2020

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

Jack Parker-Holder, Luke Metz, Cinjon Resnick, Hengyuan Hu, Adam Lerer, Alistair Letcher, Alex Peysakhovich, Aldo Pacchiano, Jakob Foerster

NeurIPS - December 7, 2020

Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees

Shali Jiang, Daniel Jiang, Max Balandat, Brian Karrer, Jacob R. Gardner, Roman Garnett

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy