CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Continual learning, Knowledge transfer, Algorithmic reasoning
TL;DR: Propose novel human-like continual learning scenario "Continual learning on algorithmic reasoning" and ways to solve it.
Abstract: Continual learning (CL) aims to incrementally learn multiple tasks that are presented sequentially. The significance of CL lies not only in the practical importance but also in studying the learning mechanisms of humans who are excellent continual learners. While most research on CL has been done on structured data such as images, there is a lack of research on CL for abstract logical concepts such as counting, sorting, and arithmetic, which humans learn gradually over time in the real world. In this work, for the first time, we introduce novel algorithmic reasoning (AR) methodology for continual tasks of abstract concepts: CLeAR. Our methodology proposes a one-to-many mapping of input distribution to a shared mapping space, which allows the alignment of various tasks of different dimensions and shared semantics. Our tasks of abstract logical concepts, in the form of formal language, can be classified into Chomsky hierarchies based on their difficulty. In this study, we conducted extensive experiments consisting of 15 tasks with various levels of Chomsky hierarchy, ranging from in-hierarchy to inter-hierarchy scenarios. CLeAR not only achieved near zero forgetting but also improved accuracy during following tasks, a phenomenon known as backward transfer, while previous CL methods designed for image classification drastically failed.
Supplementary Material: pdf
Submission Number: 7914