Toward Sustainable Continual Learning: Detection and Knowledge Repurposing of Similar Tasks

10/11/2022
by   Sijia Wang, et al.
0

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or dissimilarity among learning tasks, these methods require constantly accumulating task-specific knowledge in memory for each task. This results in the eventual prohibitive expansion of the knowledge repository if we consider learning from a long sequence of tasks. In this work, we introduce a paradigm where the continual learner gets a sequence of mixed similar and dissimilar tasks. We propose a new continual learning framework that uses a task similarity detection function that does not require additional learning, with which we analyze whether there is a specific task in the past that is similar to the current task. We can then reuse previous task knowledge to slow down parameter expansion, ensuring that the CL system expands the knowledge repository sublinearly to the number of learned tasks. Our experiments show that the proposed framework performs competitively on widely used computer vision benchmarks such as CIFAR10, CIFAR100, and EMNIST.

READ FULL TEXT

page 19

page 20

research
12/18/2021

Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks

Existing research on continual learning of a sequence of tasks focused o...
research
12/23/2020

Efficient Continual Learning with Modular Networks and Task-Driven Priors

Existing literature in Continual Learning (CL) has focused on overcoming...
research
03/31/2020

Conditional Channel Gated Networks for Task-Aware Continual Learning

Convolutional Neural Networks experience catastrophic forgetting when op...
research
05/07/2019

Continual and Multi-task Reinforcement Learning With Shared Episodic Memory

Episodic memory plays an important role in the behavior of animals and h...
research
08/16/2023

Graph Relation Aware Continual Learning

Continual graph learning (CGL) studies the problem of learning from an i...
research
10/16/2022

Navigating Memory Construction by Global Pseudo-Task Simulation for Continual Learning

Continual learning faces a crucial challenge of catastrophic forgetting....
research
11/22/2021

DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion

Deep network architectures struggle to continually learn new tasks witho...

Please sign up or login with your details

Forgot password? Click here to reset