Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cao, Xiaofeng, Xu, Mingwei, Yu, Xin, Yao, Jiangchao, Ye, Wei, Huang, Shengjun, Zhang, Minling, Tsang, Ivor W., Ong, Yew Soon, Kwok, James T., Shen, Heng Tao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.08962
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917001618784256
author Cao, Xiaofeng
Xu, Mingwei
Yu, Xin
Yao, Jiangchao
Ye, Wei
Huang, Shengjun
Zhang, Minling
Tsang, Ivor W.
Ong, Yew Soon
Kwok, James T.
Shen, Heng Tao
author_facet Cao, Xiaofeng
Xu, Mingwei
Yu, Xin
Yao, Jiangchao
Ye, Wei
Huang, Shengjun
Zhang, Minling
Tsang, Ivor W.
Ong, Yew Soon
Kwok, James T.
Shen, Heng Tao
contents Learning with high-resource data has demonstrated substantial success in artificial intelligence (AI); however, the costs associated with data annotation and model training remain significant. A fundamental objective of AI research is to achieve robust generalization with limited-resource data. This survey employs agnostic active sampling theory within the Probably Approximately Correct (PAC) framework to analyze the generalization error and label complexity associated with learning from low-resource data in both model-agnostic supervised and unsupervised settings. Based on this analysis, we investigate a suite of optimization strategies tailored for low-resource data learning, including gradient-informed optimization, meta-iteration optimization, geometry-aware optimization, and LLMs-powered optimization. Furthermore, we provide a comprehensive overview of multiple learning paradigms that can benefit from low-resource data, including domain transfer, reinforcement feedback, and hierarchical structure modeling. Finally, we conclude our analysis and investigation by summarizing the key findings and highlighting their implications for learning with low-resource data.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08962
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation
Cao, Xiaofeng
Xu, Mingwei
Yu, Xin
Yao, Jiangchao
Ye, Wei
Huang, Shengjun
Zhang, Minling
Tsang, Ivor W.
Ong, Yew Soon
Kwok, James T.
Shen, Heng Tao
Machine Learning
Artificial Intelligence
Learning with high-resource data has demonstrated substantial success in artificial intelligence (AI); however, the costs associated with data annotation and model training remain significant. A fundamental objective of AI research is to achieve robust generalization with limited-resource data. This survey employs agnostic active sampling theory within the Probably Approximately Correct (PAC) framework to analyze the generalization error and label complexity associated with learning from low-resource data in both model-agnostic supervised and unsupervised settings. Based on this analysis, we investigate a suite of optimization strategies tailored for low-resource data learning, including gradient-informed optimization, meta-iteration optimization, geometry-aware optimization, and LLMs-powered optimization. Furthermore, we provide a comprehensive overview of multiple learning paradigms that can benefit from low-resource data, including domain transfer, reinforcement feedback, and hierarchical structure modeling. Finally, we conclude our analysis and investigation by summarizing the key findings and highlighting their implications for learning with low-resource data.
title Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.08962