Iterated learning for emergent systematicity in VQA
arXiv:2105.01119
Abstract
Although neural module networks have an architectural bias towards compositionality, they require gold standard layouts to generalize systematically in practice. When instead learning layouts and modules jointly, compositionality does not arise automatically and an explicit pressure is necessary for the emergence of layouts exhibiting the right structure. We propose to address this problem using iterated learning, a cognitive science theory of the emergence of compositional languages in nature that has primarily been applied to simple referential games in machine learning. Considering the layouts of module networks as samples from an emergent language, we use iterated learning to encourage the development of structure within this language. We show that the resulting layouts support systematic generalization in neural agents solving the more complex task of visual question-answering. Our regularized iterated learning method can outperform baselines without iterated learning on SHAPES-SyGeT (SHAPES Systematic Generalization Test), a new split of the SHAPES dataset we introduce to evaluate systematic generalization, and on CLOSURE, an extension of CLEVR also designed to test systematic generalization. We demonstrate superior performance in recovering ground-truth compositional program structure with limited supervision on both SHAPES-SyGeT and CLEVR.
arXiv commentPublished as a conference paper at ICLR 2021. 9 pages main, 21 pages total including references and appendix
References in corpus (10)
- Spectral Normalization for Generative Adversarial Networks
- Categorical Reparameterization with Gumbel-Softmax
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence
- CLOSURE: Assessing Systematic Generalization of CLEVR Models
- Emergence of Compositional Language with Deep Generational Transmission
- Compositional Languages Emerge in a Neural Iterated Learning Model
- Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering
- On the interaction between supervision and self-play in emergent communication
- The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents