paper-with-me

홈 › Papers

Self-Supervised Contrastive Learning for Long-term Forecasting

2024-02-03 · Junwoo Park, Daehoon Gwak, Jaegul Choo, Edward Choi

Long-term forecasting presents unique challenges due to the time and memory complexity of handling long sequences. Existing methods, which rely on sliding windows to process long sequences, struggle to effectively capture long-term variations that are partially caught within the short window (i.e., outer-window variations). In this paper, we introduce a novel approach that overcomes this limitation by employing contrastive learning and enhanced decomposition architecture, specifically designed to focus on long-term variations. To this end, our contrastive loss incorporates global autocorrelation held in the whole time series, which facilitates the construction of positive and negative pairs in a self-supervised manner. When combined with our decomposition networks, our contrastive learning significantly improves long-term forecasting performance. Extensive experiments demonstrate that our approach outperforms 14 baseline models in multiple experiments over nine long-term benchmarks, especially in challenging scenarios that require a significantly long output for forecasting. Source code is available at https://github.com/junwoopark92/Self-Supervised-Contrastive-Forecsating.

📄 PDF Abstract BibTeX arXiv:2402.02023

Code (1)

junwoopark92/self-supervised-contrastive-forecsating 공식 구현 pytorch

Tasks

Contrastive LearningTime SeriesTime Series Forecasting

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Momentum-Guided Semantic Forecasting (MoFore) for Self-Supervised Video Representation Learning

2026-06-08 · Qinwu Xu arxiv

Self-supervised video representation learning has recently advanced through contrastive learning, masked reconstruction, and predictive representation learning. Reconstruction-based approaches such as MAE and VideoMAE le…

Representation LearningContrastive Learning

Ti-MAE: Self-Supervised Masked Time Series Autoencoders

2023-01-21 · Zhe Li, Zhongwen Rao, Lujia Pan, Pengyun Wang 외

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have achieved good performance in many long-t…

Contrastive LearningMultivariate Time Series ForecastingRepresentation LearningTime Series+2

TS2Vec-Ensemble: An Enhanced Self-Supervised Framework for Time Series Forecasting

2025-11-27 · Ganeshan Niroshan, Uthayasanker Thayasivam arxiv

Self-supervised representation learning, particularly through contrastive methods like TS2Vec, has advanced the analysis of time series data. However, these models often falter in forecasting tasks because their objectiv…

Time Series ForecastingRepresentation Learning

Contrastive Similarity Learning for Market Forecasting: The ContraSim Framework

2025-02-22 · Nicholas Vinden, Raeid Saqur, Zining Zhu, Frank Rudzicz

We introduce the Contrastive Similarity Space Embedding Algorithm (ContraSim), a novel framework for uncovering the global semantic relationships between daily financial headlines and market movements. ContraSim operates…

Contrastive Learning

Multiscale Video Pretraining for Long-Term Activity Forecasting

2023-07-24 · Reuben Tan, Matthias De Lange, Michael Iuzzolino, Bryan A. Plummer 외

Long-term activity forecasting is an especially challenging research problem because it requires understanding the temporal relationships between observed actions, as well as the variability and complexity of human activ…

Action AnticipationLong Term Action Anticipation