A Comprehensive Survey of Continual Learning: Theory, Method and Application

Abstract

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance degradation of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual learning. The growing and widespread interest in this direction demonstrates its realistic significance as well as complexity. In this work, we present a comprehensive survey of continual learning, seeking to bridge the basic settings, theoretical foundations, representative methods, and practical applications. Based on existing theoretical and empirical results, we summarize the general objectives of continual learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency. Then we provide a state-of-the-art and elaborated taxonomy, extensively analyzing how representative methods address continual learning, and how they are adapted to particular challenges in realistic applications. Through an in-depth discussion of promising directions, we believe that such a holistic perspective can greatly facilitate subsequent exploration in this field and beyond.

arXiv commentThe concise version is in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Cited by in corpus (8)

• Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review
• Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification
• A Frank System for Co-Evolutionary Hybrid Decision-Making
• DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes
• Domain Adaptation for Time series Transformers using One-step fine-tuning
• Visually Grounded Continual Language Learning with Selective Specialization
• A Simple Illustration of Interleaved Learning using Kalman Filter for Linear Least Squares
• Weighted Ensemble Models Are Strong Continual Learners