Saved in:
Bibliographic Details
Main Authors: Valkov, Lazar, Srivastava, Akash, Chaudhuri, Swarat, Sutton, Charles
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.06545
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.