paper-with-me

홈 › Papers

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

2023-09-21 · NeurIPS 2023 11

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.

📄 PDF Abstract BibTeX

Code (1)

pusheen-cat/clear_2023 공식 구현 jax

Similar Papers 제목 키워드 기반

Continual Memory: Can We Reason After Long-Term Memorization?

2021-01-01 · Zhu Zhang, Chang Zhou, Zhou Zhao, Zhijie Lin 외

Existing reasoning tasks often follow the setting of "reasoning while experiencing", which has an important assumption that the raw contents can be always accessed while reasoning. However, human beings frequently adopt …

Memorization

AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming

2025-07-21 · Jierui Li, Raymond Mooney arxiv

Recent reasoning-enhanced Large Language Models (LLMs) have achieved promising results in solving complex competitive programming problems. However, it remains unclear whether these reasoning abilities generalize to rele…

VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge

2025-04-14 · Yueqi Song, Tianyue Ou, Yibo Kong, Zecheng Li 외

Current multimodal benchmarks often conflate reasoning with domain-specific knowledge, making it difficult to isolate and evaluate general reasoning abilities in non-expert settings. To address this, we introduce VisualP…

Logical ReasoningMultimodal ReasoningSpatial ReasoningVisual Reasoning

Catastrophic Forgetting in Kolmogorov-Arnold Networks

2025-11-16 · Mohammad Marufur Rahman, Guanchu Wang, Kaixiong Zhou, Minghan Chen 외 arxiv

Catastrophic forgetting is a longstanding challenge in continual learning, where models lose knowledge from earlier tasks when learning new ones. While various mitigation strategies have been proposed for Multi-Layer Per…

Image ClassificationContinual Learningknowledge editing

Dual Algorithmic Reasoning

2023-02-09 · Danilo Numeroso, Davide Bacciu, Petar Veličković

Neural Algorithmic Reasoning is an emerging area of machine learning which seeks to infuse algorithmic computation in neural networks, typically by training neural models to approximate steps of classical algorithms. In …