paper-with-me

Papers

A Comprehensive Survey of Time Series Forecasting: Architectural Diversity and Open Challenges

2024-10-24 · Jongseon Kim, Hyungjoon Kim, HyunGi Kim, Dongjun Lee, Sungroh Yoon

Time series forecasting is a critical task that provides key information for decision-making across various fields. Recently, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs have been developed and applied to solve time series forecasting problems. However, the structural limitations caused by the inductive biases of each deep learning architecture constrained their performance. Transformer models, which excel at handling long-term dependencies, have become significant architectural components for time series forecasting. However, recent research has shown that alternatives such as simple linear layers can outperform Transformers. These findings have opened up new possibilities for using diverse architectures. In this context of exploration into various models, the architectural modeling of time series forecasting has now entered a renaissance. This survey not only provides a historical context for time series forecasting but also offers comprehensive and timely analysis of the movement toward architectural diversification. By comparing and re-examining various deep learning models, we uncover new perspectives and presents the latest trends in time series forecasting, including the emergence of hybrid models, diffusion models, Mamba models, and foundation models. By focusing on the inherent characteristics of time series data, we also address open challenges that have gained attention in time series forecasting, such as channel dependency, distribution shift, causality, and feature extraction. This survey explores vital elements that can enhance forecasting performance through diverse approaches. These contributions lead to lowering the entry barriers for newcomers to the field of time series forecasting, while also offering seasoned researchers broad perspectives, new opportunities, and deep insights.

📄 PDF Abstract BibTeX arXiv:2411.05793

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityMambaTime SeriesTime Series Forecasting

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

2023-07-07 · Ming Jin, Huan Yee Koh, Qingsong Wen, Daniele Zambon 외

Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series analytics is therefore crucial t…

Anomaly DetectionImputationSurveyTime Series+2

Deep Autocorrelation Modeling for Time-Series Forecasting: Progress and Prospects

2026-03-20 · Hao Wang, Licheng Pan, Qingsong Wen, Jialin Yu 외 arxiv

Autocorrelation is a defining characteristic of time-series data, where each observation is statistically dependent on its predecessors. In the context of deep time-series forecasting, autocorrelation arises in both the …

Diffusion Models for Time Series Forecasting: A Survey

2025-07-19 · Chen Su, Zhengzhou Cai, Yuanhe Tian, Zhuochao Chang 외 arxiv

Diffusion models, initially developed for image synthesis, demonstrate remarkable generative capabilities. Recently, their application has expanded to time series forecasting (TSF), yielding promising results. Existing s…

Time Series Forecasting

Deep Learning for Time Series Forecasting: A Survey

2025-03-13 · Xiangjie Kong, Zhenghao Chen, Weiyao Liu, Kaili Ning 외

Time series forecasting (TSF) has long been a crucial task in both industry and daily life. Most classical statistical models may have certain limitations when applied to practical scenarios in fields such as energy, hea…

Deep LearningSurveyTime SeriesTime Series Forecasting

A Survey of Deep Learning and Foundation Models for Time Series Forecasting

2024-01-25 · John A. Miller, Mohammed Aldosari, Farah Saeed, Nasid Habib Barna 외

Deep Learning has been successfully applied to many application domains, yet its advantages have been slow to emerge for time series forecasting. For example, in the well-known Makridakis (M) Competitions, hybrids of tra…

Deep LearningKnowledge GraphsTime SeriesTime Series Forecasting