Progress & Compress: A scalable framework for continual learning
We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is achieved by training a network with two components: A knowledge base, capable of solving previously encountered problems, which is connected to an active column that is employed to efficiently learn the current task. After learning a new task, the active column is distilled into the knowledge base, taking care to protect any previously acquired skills. This cycle of active learning (progression) followed by consolidation (compression) requires no architecture growth, no access to or storing of previous data or tasks, and no task-specific parameters. We demonstrate the progress & compress approach on sequential classification of handwritten alphabets as well as two reinforcement learning domains: Atari games and 3D maze navigation.
Code (1)
Tasks
Active LearningAtari GamesContinual LearningReinforcement LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ContCap: A scalable framework for continual image captioning
While advanced image captioning systems are increasingly describing images coherently and exactly, recent progress in continual learning allows deep learning models to avoid catastrophic forgetting. However, the domain w…
Continual LearningImage CaptioningVideo CaptioningCompacting, Picking and Growing for Unforgetting Continual Learning
Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the principles of deep model compression, critic…
Age And Gender ClassificationContinual LearningFace VerificationFacial Expression Recognition (FER)+3LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning
On-device learning is essential for personalization, privacy, and long-term adaptation in resource-constrained environments. Achieving this requires efficient learning, both fine-tuning existing models and continually ac…
Continual LearningOnline Learned Continual Compression with Adaptive Quantization Modules
We introduce and study the problem of Online Continual Compression, where one attempts to simultaneously learn to compress and store a representative dataset from a non i.i.d data stream, while only observing each sample…
Continual LearningDecoderQuantizationReinforcement LearningMemVerse: Multimodal Memory for Lifelong Learning Agents
Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember. Without reliable memory, agents catastrophically forget past experiences, stru…
Multimodal ReasoningContinual LearningKnowledge Graphs