HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Książek, Kamil, Spurek, Przemysław
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910458381860864
author Książek, Kamil
Spurek, Przemysław
author_facet Książek, Kamil
Spurek, Przemysław
contents Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. Many continual learning (CL) strategies are trying to overcome this problem. One of the most effective is the hypernetwork-based approach. The hypernetwork generates the weights of a target model based on the task's identity. The model's main limitation is that, in practice, the hypernetwork can produce completely different architectures for subsequent tasks. To solve such a problem, we use the lottery ticket hypothesis, which postulates the existence of sparse subnetworks, named winning tickets, that preserve the performance of a whole network. In the paper, we propose a method called HyperMask, which dynamically filters a target network depending on the CL task. The hypernetwork produces semi-binary masks to obtain dedicated target subnetworks. Moreover, due to the lottery ticket hypothesis, we can use a single network with weighted subnets. Depending on the task, the importance of some weights may be dynamically enhanced while others may be weakened. HyperMask achieves competitive results in several CL datasets and, in some scenarios, goes beyond the state-of-the-art scores, both with derived and unknown task identities.
format Preprint
id arxiv_https___arxiv_org_abs_2310_00113
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning
Książek, Kamil
Spurek, Przemysław
Machine Learning
Artificial Intelligence
68T07
I.2.6
Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. Many continual learning (CL) strategies are trying to overcome this problem. One of the most effective is the hypernetwork-based approach. The hypernetwork generates the weights of a target model based on the task's identity. The model's main limitation is that, in practice, the hypernetwork can produce completely different architectures for subsequent tasks. To solve such a problem, we use the lottery ticket hypothesis, which postulates the existence of sparse subnetworks, named winning tickets, that preserve the performance of a whole network. In the paper, we propose a method called HyperMask, which dynamically filters a target network depending on the CL task. The hypernetwork produces semi-binary masks to obtain dedicated target subnetworks. Moreover, due to the lottery ticket hypothesis, we can use a single network with weighted subnets. Depending on the task, the importance of some weights may be dynamically enhanced while others may be weakened. HyperMask achieves competitive results in several CL datasets and, in some scenarios, goes beyond the state-of-the-art scores, both with derived and unknown task identities.
title HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning
topic Machine Learning
Artificial Intelligence
68T07
I.2.6
url https://arxiv.org/abs/2310.00113