Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization

05/29/2023
by   Tao Yang, et al.
0

Recognizing elementary underlying concepts from observations (disentanglement) and generating novel combinations of these concepts (compositional generalization) are fundamental abilities for humans to support rapid knowledge learning and generalize to new tasks, with which the deep learning models struggle. Towards human-like intelligence, various works on disentangled representation learning have been proposed, and recently some studies on compositional generalization have been presented. However, few works study the relationship between disentanglement and compositional generalization, and the observed results are inconsistent. In this paper, we study several typical disentangled representation learning works in terms of both disentanglement and compositional generalization abilities, and we provide an important insight: vector-based representation (using a vector instead of a scalar to represent a concept) is the key to empower both good disentanglement and strong compositional generalization. This insight also resonates the neuroscience research that the brain encodes information in neuron population activity rather than individual neurons. Motivated by this observation, we further propose a method to reform the scalar-based disentanglement works (β-TCVAE and FactorVAE) to be vector-based to increase both capabilities. We investigate the impact of the dimensions of vector-based representation and one important question: whether better disentanglement indicates higher compositional generalization. In summary, our study demonstrates that it is possible to achieve both good concept recognition and novel concept composition, contributing an important step towards human-like intelligence.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/02/2022

Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language

Deep learning models struggle with compositional generalization, i.e. th...
research
07/10/2023

Compositional Generalization from First Principles

Leveraging the compositional nature of our world to expedite learning an...
research
02/08/2021

Concepts, Properties and an Approach for Compositional Generalization

Compositional generalization is the capacity to recognize and imagine a ...
research
03/14/2022

Revisiting the Compositional Generalization Abilities of Neural Sequence Models

Compositional generalization is a fundamental trait in humans, allowing ...
research
02/19/2019

Measuring Compositionality in Representation Learning

Many machine learning algorithms represent input data with vector embedd...
research
04/13/2020

Compositional Visual Generation and Inference with Energy Based Models

A vital aspect of human intelligence is the ability to compose increasin...
research
12/12/2022

Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning

Compositional generalization is a basic mechanism in human language lear...

Please sign up or login with your details

Forgot password? Click here to reset