Saved in:
Bibliographic Details
Main Authors: Luong, Kevin, Thielscher, Michael
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.17188
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910759458439168
author Luong, Kevin
Thielscher, Michael
author_facet Luong, Kevin
Thielscher, Michael
contents Continual Learning models aim to learn a set of tasks under the constraint that the tasks arrive sequentially with no way to access data from previous tasks. The Online Continual Learning framework poses a further challenge where the tasks are unknown and instead the data arrives as a single stream. Building on existing work, we propose a method for identifying these underlying tasks: the Gated Experts (GE) algorithm, where a dynamically growing set of experts allows for new knowledge to be acquired without catastrophic forgetting. Furthermore, we extend GE to Hierarchically Gated Experts (HGE), a method which is able to efficiently select the best expert for each data sample by organising the experts into a hierarchical structure. On standard Continual Learning benchmarks, GE and HGE are able to achieve results comparable with current methods, with HGE doing so more efficiently.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17188
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hierarchically Gated Experts for Efficient Online Continual Learning
Luong, Kevin
Thielscher, Michael
Machine Learning
Artificial Intelligence
Continual Learning models aim to learn a set of tasks under the constraint that the tasks arrive sequentially with no way to access data from previous tasks. The Online Continual Learning framework poses a further challenge where the tasks are unknown and instead the data arrives as a single stream. Building on existing work, we propose a method for identifying these underlying tasks: the Gated Experts (GE) algorithm, where a dynamically growing set of experts allows for new knowledge to be acquired without catastrophic forgetting. Furthermore, we extend GE to Hierarchically Gated Experts (HGE), a method which is able to efficiently select the best expert for each data sample by organising the experts into a hierarchical structure. On standard Continual Learning benchmarks, GE and HGE are able to achieve results comparable with current methods, with HGE doing so more efficiently.
title Hierarchically Gated Experts for Efficient Online Continual Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.17188