A Theory for Knowledge Transfer in Continual Learning

08/14/2022
by   Diana Benavides-Prado, et al.
0

Continual learning of a stream of tasks is an active area in deep neural networks. The main challenge investigated has been the phenomenon of catastrophic forgetting or interference of newly acquired knowledge with knowledge from previous tasks. Recent work has investigated forward knowledge transfer to new tasks. Backward transfer for improving knowledge gained during previous tasks has received much less attention. There is in general limited understanding of how knowledge transfer could aid tasks learned continually. We present a theory for knowledge transfer in continual supervised learning, which considers both forward and backward transfer. We aim at understanding their impact for increasingly knowledgeable learners. We derive error bounds for each of these transfer mechanisms. These bounds are agnostic to specific implementations (e.g. deep neural networks). We demonstrate that, for a continual learner that observes related tasks, both forward and backward transfer can contribute to an increasing performance as more tasks are observed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/14/2023

Is forgetting less a good inductive bias for forward transfer?

One of the main motivations of studying continual learning is that the p...
research
05/05/2023

On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning

Humans can learn incrementally, whereas neural networks forget previousl...
research
07/14/2020

Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer

We introduce the eigentask framework for lifelong learning. An eigentask...
research
08/23/2020

Learn to Talk via Proactive Knowledge Transfer

Knowledge Transfer has been applied in solving a wide variety of problem...
research
05/01/2021

A Deep Learning Framework for Lifelong Machine Learning

Humans can learn a variety of concepts and skills incrementally over the...
research
07/22/2021

Learning to Transfer: A Foliated Theory

Learning to transfer considers learning solutions to tasks in a such way...
research
04/27/2020

A general approach to progressive learning

In biological learning, data is used to improve performance on the task ...

Please sign up or login with your details

Forgot password? Click here to reset