HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning

Kamil Książek, Przemysław Spurek

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Continual Learning, Hypernetworks, lottery ticket hypothesis

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a method called HyperMask, which trains a single network for all tasks and uses hypernetwork to produce semi-binary masks to obtain target subnetworks dedicated to new tasks.

Abstract:

Artificial neural networks suffer catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, there exist many continual learning strategies. 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 hypernetwork can produce completely different nests for each task. Consequently, each task is solved separately.
The model does not use information from the network dedicated to previous tasks.
We practically produce a new architecture when we update the prior task.
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 full network.

In the paper, we propose a method called HyperMask, which trains a single network for all tasks. Hypernetwork produces semi-binary masks to obtain target subnetworks dedicated to new tasks. This solution inherits the ability of the hypernetwork to adapt to new tasks with minimal forgetting. Moreover, due to the lottery ticket hypothesis, we can use a single network with weighted subnets dedicated to each task.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1307