English
Related papers

Related papers: Revisiting Attention for Multivariate Time Series …

200 papers

Recently, Transformer-based models for long sequence time series forecasting have demonstrated promising results. The self-attention mechanism as the core component of these Transformer-based models exhibits great potential in capturing…

Machine Learning · Computer Science 2024-12-17 Zhicheng Zhang , Yong Wang , Shaoqi Tan , Bowei Xia , Yujie Luo

Time series forecasting is widely used in the fields of equipment life cycle forecasting, weather forecasting, traffic flow forecasting, and other fields. Recently, some scholars have tried to apply Transformer to time series forecasting…

Machine Learning · Computer Science 2022-02-24 Benhan Li , Shengdong Du , Tianrui Li

The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Transformers are computationally expensive at inference time,…

Machine Learning · Computer Science 2024-05-29 Leo Feng , Frederick Tung , Hossein Hajimirsadeghi , Mohamed Osama Ahmed , Yoshua Bengio , Greg Mori

Despite the notable advancements in numerous Transformer-based models, the task of long multi-horizon time series forecasting remains a persistent challenge, especially towards explainability. Focusing on commonly used saliency maps in…

Machine Learning · Computer Science 2023-09-18 Nghia Duong-Trung , Duc-Manh Nguyen , Danh Le-Phuoc

There has been a recent surge of interest in time series modeling using the Transformer architecture. However, forecasting multivariate time series with Transformer presents a unique challenge as it requires modeling both temporal…

Machine Learning · Computer Science 2025-07-04 Yu-Hsiang Lan , Eric K. Oermann

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

Computation and Language · Computer Science 2023-10-24 Yinghan Long , Sayeed Shafayet Chowdhury , Kaushik Roy

The diversity of time series applications and scarcity of domain-specific data highlight the need for time-series models with strong few-shot learning capabilities. In this work, we propose a novel training scheme and a transformer-based…

Machine Learning · Computer Science 2025-02-25 Ege Onur Taga , M. Emrullah Ildiz , Samet Oymak

Transformer-based models have recently become dominant in Long-term Time Series Forecasting (LTSF), yet the variations in their architecture, such as encoder-only, encoder-decoder, and decoder-only designs, raise a crucial question: What…

Machine Learning · Computer Science 2025-07-18 Lefei Shen , Mouxiang Chen , Han Fu , Xiaoxue Ren , Xiaoyun Joy Wang , Jianling Sun , Zhuo Li , Chenghao Liu

Multivariate Time Series Forecasting (MTSF) plays a crucial role across diverse fields, ranging from economic, energy, to traffic. In recent years, deep learning has demonstrated outstanding performance in MTSF tasks. In MTSF, modeling the…

Machine Learning · Computer Science 2026-01-28 Xiangfei Qiu , Hanyin Cheng , Xingjian Wu , Junkai Lu , Jilin Hu , Chenjuan Guo , Christian S. Jensen , Bin Yang

Time series forecasting is an important problem across many domains, playing a crucial role in multiple real-world applications. In this paper, we propose a forecasting architecture that combines deep autoregressive models with a Spectral…

Machine Learning · Statistics 2021-12-28 Fernando Moreno-Pino , Pablo M. Olmos , Antonio Artés-Rodríguez

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years. In addition to learning attention in time domain, recent works also explore learning attention in…

Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio. High-quality spectrum models usually…

Sound · Computer Science 2021-04-05 Qing He , Zhiping Xiu , Thilo Koehler , Jilong Wu

In multivariate time series (MTS) classification, finding the important features (e.g., sensors) for model performance is crucial yet challenging due to the complex, high-dimensional nature of MTS data, intricate temporal dynamics, and the…

Machine Learning · Computer Science 2024-06-13 Jaeho Kim , Seok-Ju Hahn , Yoontae Hwang , Junghye Lee , Seulki Lee

Multivariate time series (MTS) forecasting is vital in fields like weather, energy, and finance. However, despite deep learning advancements, traditional Transformer-based models often diminish the effect of crucial inter-variable…

Machine Learning · Computer Science 2025-03-03 Yanhong Li , David C. Anastasiu

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same…

Machine Learning · Computer Science 2024-11-21 Xuechen Zhang , Xiangyu Chang , Mingchen Li , Amit Roy-Chowdhury , Jiasi Chen , Samet Oymak

Sufficiently modeling the correlations among variables (aka channels) is crucial for achieving accurate multivariate time series forecasting (MTSF). In this paper, we propose a novel technique called Temporal Query (TQ) to more effectively…

Machine Learning · Computer Science 2025-09-12 Shengsheng Lin , Haojun Chen , Haijie Wu , Chunyun Qiu , Weiwei Lin

Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary…

Machine Learning · Computer Science 2026-05-19 Sumit S Shevtekar , Chandresh K Maurya

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-28 Rui Wang , Junyi Ao , Long Zhou , Shujie Liu , Zhihua Wei , Tom Ko , Qing Li , Yu Zhang

Transformers have demonstrated their effectiveness in image restoration tasks. Existing Transformer architectures typically comprise two essential components: multi-head self-attention and feed-forward network (FFN). The former captures…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Cong Wang , Jinshan Pan , Yeying Jin , Liyan Wang , Wei Wang , Gang Fu , Wenqi Ren , Xiaochun Cao

The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an…

Computation and Language · Computer Science 2017-07-04 Denny Britz , Melody Y. Guan , Minh-Thang Luong