Online Continual Learning under Extreme Memory Constraints

by   Enrico Fini, et al.
Università di Trento

Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In this paper, we introduce the novel problem of Memory-Constrained Online Continual Learning (MC-OCL) which imposes strict constraints on the memory overhead that a possible algorithm can use to avoid catastrophic forgetting. As most, if not all, previous CL methods violate these constraints, we propose an algorithmic solution to MC-OCL: Batch-level Distillation (BLD), a regularization-based CL approach, which effectively balances stability and plasticity in order to learn from data streams, while preserving the ability to solve old tasks through distillation. Our extensive experimental evaluation, conducted on three publicly available benchmarks, empirically demonstrates that our approach successfully addresses the MC-OCL problem and achieves comparable accuracy to prior distillation methods requiring higher memory overhead.


page 1

page 2

page 3

page 4


New Insights for the Stability-Plasticity Dilemma in Online Continual Learning

The aim of continual learning is to learn new tasks continuously (i.e., ...

Selecting Related Knowledge via Efficient Channel Attention for Online Continual Learning

Continual learning aims to learn a sequence of tasks by leveraging the k...

Centroid Distance Distillation for Effective Rehearsal in Continual Learning

Rehearsal, retraining on a stored small data subset of old tasks, has be...

CBA: Improving Online Continual Learning via Continual Bias Adaptor

Online continual learning (CL) aims to learn new knowledge and consolida...

Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer

We focus on the problem of teaching a robot to solve tasks presented seq...

Information-theoretic Online Memory Selection for Continual Learning

A challenging problem in task-free continual learning is the online sele...

Structured Ensembles: an Approach to Reduce the Memory Footprint of Ensemble Methods

In this paper, we propose a novel ensembling technique for deep neural n...

Please sign up or login with your details

Forgot password? Click here to reset