• Home
  • Search
  • Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning
  • Cite Icon3
  • https://doi.org/10.1609/aaai.v39i16.33828Copy DOI Icon

Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning

  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Contrastive learning underpins most current self-supervised time series representation methods. The strategy for constructing positive and negative sample pairs significantly affects the final representation quality. However, due to the continuous nature of time series semantics, the modeling approach of contrastive learning struggles to accommodate the characteristics of time series data. This results in issues such as difficulties in constructing hard negative samples and the potential introduction of inappropriate biases during positive sample construction. Although some recent works have developed several scientific strategies for constructing positive and negative sample pairs with improved effectiveness, they remain constrained by the contrastive learning framework. To fundamentally overcome the limitations of contrastive learning, this paper introduces Frequency-masked Embedding Inference (FEI), a novel non-contrastive method that completely eliminates the need for positive and negative samples. The proposed FEI constructs 2 inference branches based on a prompting strategy: 1) Using frequency masking as prompts to infer the embedding representation of the target series with missing frequency bands in the embedding space, and 2) Using the target series as prompts to infer its frequency masking embedding. In this way, FEI enables continuous semantic relationship modeling for time series. Experiments on 8 widely used time series datasets for classification and regression tasks, using linear evaluation and end-to-end fine-tuning, show that FEI significantly outperforms existing contrastive-based methods in terms of generalization. This study provides new insights into self-supervised representation learning for time series.

Similar Papers
  • Research Article

Attack-Augmented Mixing-Contrastive Skeletal Representation Learning.

  • Jan 01, 2026
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Binqian Xu +4
  • Research Article
  • Citations28

An adversarial contrastive autoencoder for robust multivariate time series anomaly detection

  • Dec 29, 2023
  • Expert Systems with Applications
  • Jiahao Yu +7
  • Research Article
  • Citations4

Contrastive learning enhanced by graph neural networks for Universal Multivariate Time Series Representation

  • Jul 25, 2024
  • Information Systems
  • Xinghao Wang +3
  • Research Article
  • Citations2

Consistent positive correlation sample distribution: Alleviating the negative sample noise issue in contrastive adaptation

  • Nov 14, 2024
  • Expert Systems With Applications
  • Xing Wei +6
  • Conference Article
  • Citations63

Solving Inefficiency of Self-supervised Representation Learning

  • Oct 01, 2021
  • Guangrun Wang +4
  • Book Chapter
  • Citations74

Global Distance-Distributions Separation for Unsupervised Person Re-identification

  • Jan 01, 2020
  • Xin Jin +3
  • Research Article
  • Citations3

Multiscale Subgraph Adversarial Contrastive Learning.

  • Aug 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Yanbei Liu +6
  • Research Article
  • Citations27

FALSE: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Zhaoyang Zhang +4
  • Conference Article

Constructing Negative Sample Pairs to Mitigate Language Priors in Medical Visual Question Answering

  • Dec 27, 2024
  • Hao Cong +4
  • Conference Article

Graph Self-Contrast Representation Learning

  • Dec 01, 2023
  • Minjie Chen +4
  • Research Article

VGCL-DNSO: a graph contrastive learning method for identifying hidden faults under strong noise interference

  • Feb 18, 2026
  • Structural Health Monitoring
  • Haiyang Pan +5
  • Research Article
  • Citations133

Cluster-Guided Contrastive Graph Clustering Network

  • Jun 26, 2023
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Xihong Yang +8
  • Research Article
  • Citations3

Contrastive learning with semantic consistency constraint

  • Jun 28, 2023
  • Image and Vision Computing
  • Huijie Guo +1
  • Conference Article
  • Citations31

Dynamic cascades with bidirectional bootstrapping for spontaneous facial action unit detection

  • Sep 01, 2009
  • Yunfeng Zhu +3
  • Research Article
  • Citations1

Contrastive Multi-view Subspace Clustering via Tensor Transformers Autoencoder

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Qianqian Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.