Online Learned Continual Compression with Stacked Quantization Module

by   Lucas Caccia, et al.

We introduce and study the problem of Online Continual Compression, where one attempts to learn to compress and store a representative dataset from a non i.i.d data stream, while only observing each sample once. This problem is highly relevant for downstream online continual learning tasks, as well as standard learning methods under resource constrained data collection. To address this we propose a new architecture which Stacks Quantization Modules (SQM), consisting of a series of discrete autoencoders, each equipped with their own memory. Every added module is trained to reconstruct the latent space of the previous module using fewer bits, allowing the learned representation to become more compact as training progresses. This modularity has several advantages: 1) moderate compressions are quickly available early in training, which is crucial for remembering the early tasks, 2) as more data needs to be stored, earlier data becomes more compressed, freeing memory, 3) unlike previous methods, our approach does not require pretraining, even on challenging datasets. We show several potential applications of this method. We first replace the episodic memory used in Experience Replay with SQM, leading to significant gains on standard continual learning benchmarks using a fixed memory budget. We then apply our method to online compression of larger images like those from Imagenet, and show that it is also effective with other modalities, such as LiDAR data.



There are no comments yet.


page 9


ACAE-REMIND for Online Continual Learning with Compressed Feature Replay

Online continual learning aims to learn from a non-IID stream of data fr...

Online Continual Learning Via Candidates Voting

Continual learning in online scenario aims to learn a sequence of new ta...

Continual Learning from the Perspective of Compression

Connectionist models such as neural networks suffer from catastrophic fo...

Adversarial Shapley Value Experience Replay for Task-Free Continual Learning

Continual learning is a branch of deep learning that seeks to strike a b...

One Pass ImageNet

We present the One Pass ImageNet (OPIN) problem, which aims to study the...

A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays

In the last few years, research and development on Deep Learning models ...

Scalable Recollections for Continual Lifelong Learning

Given the recent success of Deep Learning applied to a variety of single...

Code Repositories


Code for "Online Learned Continual Compression with Adaptive Quantization Modules"

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.