Concept Representation Learning with Contrastive Self-Supervised Learning

TL;DR

This paper explores how contrastive self-supervised learning can be used to learn concept representations in deep learning, enabling learning with minimal supervision, adaptability to new data distributions, and integration with symbolic AI.

Contribution

It provides a comprehensive discussion of concept representation learning using CSSL, including dual-level representations, incremental learning, and relational reasoning, grounded in cognitive science insights.

Findings

CSSL supports incremental and continual learning.

It enables concept representations without semantic labels.

The approach aligns with cognitive neural science findings.

Abstract

Concept-oriented deep learning (CODL) is a general approach to meet the future challenges for deep learning: (1) learning with little or no external supervision, (2) coping with test examples that come from a different distribution than the training examples, and (3) integrating deep learning with symbolic AI. In CODL, as in human learning, concept representations are learned based on concept exemplars. Contrastive self-supervised learning (CSSL) provides a promising approach to do so, since it: (1) uses data-driven associations, to get away from semantic labels, (2) supports incremental and continual learning, to get away from (large) fixed datasets, and (3) accommodates emergent objectives, to get away from fixed objectives (tasks). We discuss major aspects of concept representation learning using CSSL. These include dual-level concept representations, CSSL for feature representations, exemplar similarity measures and self-supervised relational reasoning, incremental and continual CSSL, and contrastive self-supervised concept (class) incremental learning. The discussion leverages recent findings from cognitive neural science and CSSL.