Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings
Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized a process, ``iterated learning,'' to help explain how human language developed this ability; the theory rests on simultaneous pressures towards compressibility (when an ignorant agent learns from an informed one) and expressivity (when it uses the representation for downstream tasks). Inspired by this process, we propose to improve the compositional generalization of deep networks by using iterated learning on models with simplicial embeddings, which can approximately discretize representations. This approach is further motivated by an analysis of compositionality based on Kolmogorov complexity. We show that this combination of changes improves compositional generalization over other approaches, demonstrating these improvements both on vision tasks with well-understood latent factors and on real molecular graph prediction tasks where the latent structure is unknown.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Iterated learning for emergent systematicity in VQA
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, composi…
Question AnsweringSystematic GeneralizationVisual Question AnsweringVisual Question Answering (VQA)Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents
Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of enviro…
Reinforcement LearningOutlier Detection for Trajectories via Flow-embeddings
We propose a method to detect outliers in empirically observed trajectories on a discrete or discretized manifold modeled by a simplicial complex. Our approach is similar to spectral embeddings such as diffusion-maps and…
Outlier DetectionSimplicial Embeddings in Self-Supervised Learning and Downstream Classification
Simplicial Embeddings (SEM) are representations learned through self-supervised learning (SSL), wherein a representation is projected into $L$ simplices of $V$ dimensions each using a softmax operation. This procedure co…
ClassificationInductive BiasSelf-Supervised LearningCompositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation used to condition diffusion models from th…
Self-Supervised LearningText-to-Image Generation