Saved in:
Bibliographic Details
Main Authors: Fang, Di, Zhu, Yinan, Fang, Runze, Chen, Cen, Zeng, Ziqian, Zhuang, Huiping
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.10349
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911995709620224
author Fang, Di
Zhu, Yinan
Fang, Runze
Chen, Cen
Zeng, Ziqian
Zhuang, Huiping
author_facet Fang, Di
Zhu, Yinan
Fang, Runze
Chen, Cen
Zeng, Ziqian
Zhuang, Huiping
contents Continual learning enables AI models to learn new data sequentially without retraining in real-world scenarios. Most existing methods assume the training data are balanced, aiming to reduce the catastrophic forgetting problem that models tend to forget previously generated data. However, data imbalance and the mixture of new and old data in real-world scenarios lead the model to ignore categories with fewer training samples. To solve this problem, we propose an analytic imbalance rectifier algorithm (AIR), a novel online exemplar-free continual learning method with an analytic (i.e., closed-form) solution for data-imbalanced class-incremental learning (CIL) and generalized CIL scenarios in real-world continual learning. AIR introduces an analytic re-weighting module (ARM) that calculates a re-weighting factor for each class for the loss function to balance the contribution of each category to the overall loss and solve the problem of imbalanced training data. AIR uses the least squares technique to give a non-discriminatory optimal classifier and its iterative update method in continual learning. Experimental results on multiple datasets show that AIR significantly outperforms existing methods in long-tailed and generalized CIL scenarios. The source code is available at https://github.com/fang-d/AIR.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10349
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AIR: Analytic Imbalance Rectifier for Continual Learning
Fang, Di
Zhu, Yinan
Fang, Runze
Chen, Cen
Zeng, Ziqian
Zhuang, Huiping
Machine Learning
Computer Vision and Pattern Recognition
I.2.6
Continual learning enables AI models to learn new data sequentially without retraining in real-world scenarios. Most existing methods assume the training data are balanced, aiming to reduce the catastrophic forgetting problem that models tend to forget previously generated data. However, data imbalance and the mixture of new and old data in real-world scenarios lead the model to ignore categories with fewer training samples. To solve this problem, we propose an analytic imbalance rectifier algorithm (AIR), a novel online exemplar-free continual learning method with an analytic (i.e., closed-form) solution for data-imbalanced class-incremental learning (CIL) and generalized CIL scenarios in real-world continual learning. AIR introduces an analytic re-weighting module (ARM) that calculates a re-weighting factor for each class for the loss function to balance the contribution of each category to the overall loss and solve the problem of imbalanced training data. AIR uses the least squares technique to give a non-discriminatory optimal classifier and its iterative update method in continual learning. Experimental results on multiple datasets show that AIR significantly outperforms existing methods in long-tailed and generalized CIL scenarios. The source code is available at https://github.com/fang-d/AIR.
title AIR: Analytic Imbalance Rectifier for Continual Learning
topic Machine Learning
Computer Vision and Pattern Recognition
I.2.6
url https://arxiv.org/abs/2408.10349