Rethinking Time Encoding via Learnable Transformation Functions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xi, Tang, Yateng, Xu, Jiarong, Zhang, Jiawei, Zhang, Siwei, Peng, Sijia, Zheng, Xuehao, Xiong, Yun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909609995796480
author Chen, Xi
Tang, Yateng
Xu, Jiarong
Zhang, Jiawei
Zhang, Siwei
Peng, Sijia
Zheng, Xuehao
Xiong, Yun
author_facet Chen, Xi
Tang, Yateng
Xu, Jiarong
Zhang, Jiawei
Zhang, Siwei
Peng, Sijia
Zheng, Xuehao
Xiong, Yun
contents Effectively modeling time information and incorporating it into applications or models involving chronologically occurring events is crucial. Real-world scenarios often involve diverse and complex time patterns, which pose significant challenges for time encoding methods. While previous methods focus on capturing time patterns, many rely on specific inductive biases, such as using trigonometric functions to model periodicity. This narrow focus on single-pattern modeling makes them less effective in handling the diversity and complexities of real-world time patterns. In this paper, we investigate to improve the existing commonly used time encoding methods and introduce Learnable Transformation-based Generalized Time Encoding (LeTE). We propose using deep function learning techniques to parameterize non-linear transformations in time encoding, making them learnable and capable of modeling generalized time patterns, including diverse and complex temporal dynamics. By enabling learnable transformations, LeTE encompasses previous methods as specific cases and allows seamless integration into a wide range of tasks. Through extensive experiments across diverse domains, we demonstrate the versatility and effectiveness of LeTE.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00887
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rethinking Time Encoding via Learnable Transformation Functions
Chen, Xi
Tang, Yateng
Xu, Jiarong
Zhang, Jiawei
Zhang, Siwei
Peng, Sijia
Zheng, Xuehao
Xiong, Yun
Machine Learning
Artificial Intelligence
Effectively modeling time information and incorporating it into applications or models involving chronologically occurring events is crucial. Real-world scenarios often involve diverse and complex time patterns, which pose significant challenges for time encoding methods. While previous methods focus on capturing time patterns, many rely on specific inductive biases, such as using trigonometric functions to model periodicity. This narrow focus on single-pattern modeling makes them less effective in handling the diversity and complexities of real-world time patterns. In this paper, we investigate to improve the existing commonly used time encoding methods and introduce Learnable Transformation-based Generalized Time Encoding (LeTE). We propose using deep function learning techniques to parameterize non-linear transformations in time encoding, making them learnable and capable of modeling generalized time patterns, including diverse and complex temporal dynamics. By enabling learnable transformations, LeTE encompasses previous methods as specific cases and allows seamless integration into a wide range of tasks. Through extensive experiments across diverse domains, we demonstrate the versatility and effectiveness of LeTE.
title Rethinking Time Encoding via Learnable Transformation Functions
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.00887