A Probabilistic Framework for Modular Continual Learning
Modular approaches that use a different composition of modules for each problem are a promising direction in continual learning (CL). However, searching through the large, discrete space of module compositions is challenging, especially because evaluating a composition's performance requires a round of neural network training. We address this challenge through a modular CL framework, PICLE, that uses a probabilistic model to cheaply compute the fitness of each composition, allowing PICLE to achieve both perceptual, few-shot and latent transfer. The model combines prior knowledge about good module compositions with dataset-specific information. We evaluate PICLE using two benchmark suites designed to assess different desiderata of CL techniques. Comparing to a wide range of approaches, we show that PICLE is the first modular CL algorithm to achieve perceptual, few-shot and latent transfer while scaling well to large search spaces, outperforming previous state-of-the-art modular CL approaches on long problem sequences.
Code (1)
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning
While Large Language Models (LLMs) have catalyzed progress in embodied intelligence, a fundamental gap between their inherent probabilistic uncertainty and the strict determinism and verifiable safety required in the phy…
Continual LearningRehearsal-Free Modular and Compositional Continual Learning for Language Models
Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge. To overcome catastrophic forgetting, methods are either rehearsal-based, i.e., store data examples from previous t…
Continual LearningTransfer LearningPosition: Modular Memory is the Key to Continual Learning Agents
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these models remain fundamentally limited in c…
Continual LearningModular Deep Probabilistic Programming
Modularity is a key feature of deep learning libraries but has not been fully exploited for probabilistic programming. We propose to improve modularity of probabilistic programming language by offering not only plain pro…
Probabilistic ProgrammingVariational InferenceModular Delta Merging with Orthogonal Constraints: A Scalable Framework for Continual and Reversible Model Composition
In real-world machine learning deployments, models must be continually updated, composed, and when required, selectively undone. However, existing approaches to model merging and continual learning often suffer from task…
Continual Learning