Self-Supervised Contrastive Learning for Long-term Forecasting
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.
Code (1)
Tasks
Contrastive LearningTime SeriesTime Series ForecastingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Momentum-Guided Semantic Forecasting (MoFore) for Self-Supervised Video Representation Learning
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 LearningTi-MAE: Self-Supervised Masked Time Series Autoencoders
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+2TS2Vec-Ensemble: An Enhanced Self-Supervised Framework for Time Series Forecasting
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 LearningContrastive Similarity Learning for Market Forecasting: The ContraSim Framework
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 LearningMultiscale Video Pretraining for Long-Term Activity Forecasting
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