Online hyperparameter optimization for class-incremental learning

Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old knowledge and keep plastic to absorb new knowledge. However...

Full description

Saved in:
Bibliographic Details
Main Authors: LIU, Yaoyao, LI, Yingying, SCHIELE, Bernt, SUN, Qianru
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7559
https://ink.library.smu.edu.sg/context/sis_research/article/8562/viewcontent/AAAI2023_Online_Hyperparameter_Optimization_CIL.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8562
record_format dspace
spelling sg-smu-ink.sis_research-85622022-11-29T07:00:41Z Online hyperparameter optimization for class-incremental learning LIU, Yaoyao LI, Yingying SCHIELE, Bernt SUN, Qianru Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old knowledge and keep plastic to absorb new knowledge. However, none of the existing CIL models can achieve the optimal tradeoff in different data-receiving settings—where typically the training-from-half (TFH) setting needs more stability, but the training-from-scratch (TFS) needs more plasticity. To this end, we design an online learning method that can adaptively optimize the tradeoff without knowing the setting as a priori. Specifically, we first introduce the key hyperparameters that influence the tradeoff, e.g., knowledge distillation (KD) loss weights, learning rates, and classifier types. Then, we formulate the hyperparameter optimization process as an online Markov Decision Process (MDP) problem and propose a specific algorithm to solve it. We apply local estimated rewards and a classic bandit algorithm Exp3 (Auer et al. 2002) to address the issues when applying online MDP methods to the CIL protocol. Our method consistently improves top-performing CIL methods in both TFH and TFS settings, e.g., boosting the average accuracy of TFH and TFS by 2.2 percentage points on ImageNet-Full, compared to the state-of-the-art (Liu et al. 2021b). 2023-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7559 https://ink.library.smu.edu.sg/context/sis_research/article/8562/viewcontent/AAAI2023_Online_Hyperparameter_Optimization_CIL.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Artificial Intelligence and Robotics Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Artificial Intelligence and Robotics
Databases and Information Systems
spellingShingle Artificial Intelligence and Robotics
Databases and Information Systems
LIU, Yaoyao
LI, Yingying
SCHIELE, Bernt
SUN, Qianru
Online hyperparameter optimization for class-incremental learning
description Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old knowledge and keep plastic to absorb new knowledge. However, none of the existing CIL models can achieve the optimal tradeoff in different data-receiving settings—where typically the training-from-half (TFH) setting needs more stability, but the training-from-scratch (TFS) needs more plasticity. To this end, we design an online learning method that can adaptively optimize the tradeoff without knowing the setting as a priori. Specifically, we first introduce the key hyperparameters that influence the tradeoff, e.g., knowledge distillation (KD) loss weights, learning rates, and classifier types. Then, we formulate the hyperparameter optimization process as an online Markov Decision Process (MDP) problem and propose a specific algorithm to solve it. We apply local estimated rewards and a classic bandit algorithm Exp3 (Auer et al. 2002) to address the issues when applying online MDP methods to the CIL protocol. Our method consistently improves top-performing CIL methods in both TFH and TFS settings, e.g., boosting the average accuracy of TFH and TFS by 2.2 percentage points on ImageNet-Full, compared to the state-of-the-art (Liu et al. 2021b).
format text
author LIU, Yaoyao
LI, Yingying
SCHIELE, Bernt
SUN, Qianru
author_facet LIU, Yaoyao
LI, Yingying
SCHIELE, Bernt
SUN, Qianru
author_sort LIU, Yaoyao
title Online hyperparameter optimization for class-incremental learning
title_short Online hyperparameter optimization for class-incremental learning
title_full Online hyperparameter optimization for class-incremental learning
title_fullStr Online hyperparameter optimization for class-incremental learning
title_full_unstemmed Online hyperparameter optimization for class-incremental learning
title_sort online hyperparameter optimization for class-incremental learning
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/7559
https://ink.library.smu.edu.sg/context/sis_research/article/8562/viewcontent/AAAI2023_Online_Hyperparameter_Optimization_CIL.pdf
_version_ 1770576372541947904