DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification

doi:arXiv:2501.18116

KMS > 数学科学研究所

	DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification
	Jiang, Siyuan; Hu, Yihan; Li, Wenjie; Zeng, Pengcheng
	2025-01-30
状态	已发表
摘要	Functional data analysis (FDA) is essential for analyzing continuous, high-dimensional data, yet existing methods often decouple functional registration and classification, limiting their efficiency and performance. We present DeepFRC, an end-to-end deep learning framework that unifies these tasks within a single model. Our approach incorporates an alignment module that learns time warping functions via elastic function registration and a learnable basis representation module for dimensionality reduction on aligned data. This integration enhances both alignment accuracy and predictive performance. Theoretical analysis establishes that DeepFRC achieves low misalignment and generalization error, while simulations elucidate the progression of registration, reconstruction, and classification during training. Experiments on real-world datasets demonstrate that DeepFRC consistently outperforms state-of-the-art methods, particularly in addressing complex registration challenges. Code is available at: https://github.com/Drivergo-93589/DeepFRC.
语种	英语
DOI	arXiv:2501.18116
相关网址	查看原文
出处	Arxiv
收录类别	PPRN.PPRN
WOS记录号	PPRN:121032688
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Statistics& Probability
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/507031
专题	数学科学研究所信息科学与技术学院_硕士生数学科学研究所_PI研究组(P)_曾鹏程组数学科学研究所_本科生
通讯作者	Zeng, Pengcheng
作者单位	ShanghaiTech Univ, Inst Math Sci, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Siyuan,Hu, Yihan,Li, Wenjie,et al. DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification. 2025.