Neuro-Symbolic Concepts

TL;DR

This paper introduces a neuro-symbolic concept-centric framework enabling agents to learn continually, reason flexibly, and generalize across diverse tasks by grounding symbolic concepts in sensory data and neural representations.

Contribution

It proposes a novel neuro-symbolic concept paradigm that combines symbolic and neural methods for flexible, data-efficient, and compositional learning and reasoning.

Findings

Enhanced data efficiency in learning tasks

Improved compositional generalization capabilities

Effective zero-shot transfer across domains

Abstract

This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and action concepts, are grounded on sensory inputs and actuation outputs. They are also compositional, allowing for the creation of novel concepts through their structural combination. To facilitate learning and reasoning, the concepts are typed and represented using a combination of symbolic programs and neural network representations. Leveraging such neuro-symbolic concepts, the agent can efficiently learn and recombine them to solve various tasks across different domains, ranging from 2D images, videos, 3D scenes, and robotic manipulation tasks. This concept-centric framework offers several advantages, including data efficiency, compositional generalization, continual learning, and zero-shot transfer.