English
Related papers

Related papers: Two Steps Forward and One Behind: Rethinking Time …

200 papers

Transformers have been actively studied for time-series forecasting in recent years. While often showing promising results in various scenarios, traditional Transformers are not designed to fully exploit the characteristics of time-series…

Machine Learning · Computer Science 2022-06-22 Gerald Woo , Chenghao Liu , Doyen Sahoo , Akshat Kumar , Steven Hoi

Multivariate time series forecasting is crucial across a wide range of domains. While presenting notable progress for the Transformer architecture, iTransformer still lags behind the latest MLP-based models. We attribute this performance…

Machine Learning · Computer Science 2025-11-12 Zhiwei Zhang , Xinyi Du , Xuanchi Guo , Weihao Wang , Wenjuan Han

Transformer-based models for transfer learning have the potential to achieve high prediction accuracies on text-based supervised learning tasks with relatively few training data instances. These models are thus likely to benefit social…

Computation and Language · Computer Science 2022-09-01 Sandra Wankmüller

With the rapid development of artificial intelligence, long short term memory (LSTM), one kind of recurrent neural network (RNN), has been widely applied in time series prediction. Like RNN, Transformer is designed to handle the sequential…

Trading and Market Microstructure · Quantitative Finance 2023-09-21 Paul Bilokon , Yitao Qiu

The Transformer architecture has revolutionized the field of sequence modeling and underpins the recent breakthroughs in large language models (LLMs). However, a comprehensive mathematical theory that explains its structure and operations…

Machine Learning · Computer Science 2026-04-14 Xue-Cheng Tai , Hao Liu , Lingfeng Li , Raymond H. Chan

Reliable uncertainty quantification is critical in multivariate time series forecasting problems arising in domains such as energy systems and transportation networks, among many others. Although Transformer-based architectures have…

Machine Learning · Computer Science 2026-03-13 Rajdeep Pathak , Rahul Goswami , Madhurima Panja , Palash Ghosh , Tanujit Chakraborty

Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation…

Machine Learning · Computer Science 2019-07-15 Zhiwei Wang , Yao Ma , Zitao Liu , Jiliang Tang

Many methods for time-series forecasting are known in classical statistics, such as autoregression, moving averages, and exponential smoothing. The DeepAR framework is a novel, recent approach for time-series forecasting based on deep…

Machine Learning · Computer Science 2023-02-23 Ayla Jungbluth , Johannes Lederer

The self-attention mechanism in Transformer architecture, invariant to sequence order, necessitates positional embeddings to encode temporal order in time series prediction. We argue that this reliance on positional embeddings restricts the…

Machine Learning · Computer Science 2024-08-21 Yongbo Yu , Weizhong Yu , Feiping Nie , Xuelong Li

Transformer models have achieved state-of-the-art results across a diverse range of domains. However, concern over the cost of training the attention mechanism to learn complex dependencies between distant inputs continues to grow. In…

As Transformer-based models have achieved impressive performance on various time series tasks, Long-Term Series Forecasting (LTSF) tasks have also received extensive attention in recent years. However, due to the inherent computational…

Machine Learning · Computer Science 2024-02-06 Daojun Liang , Haixia Zhang , Dongfeng Yuan , Xiaoyan Ma , Dongyang Li , Minggao Zhang

With the development of Artificial Intelligence, numerous real-world tasks have been accomplished using technology integrated with deep learning. To achieve optimal performance, deep neural networks typically require large volumes of data…

Machine Learning · Computer Science 2025-05-09 Yuren Zhang , Zhongnan Pu , Lei Jing

The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjoy a favorable ability of fitting data, there are still…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Zhengsu Chen , Lingxi Xie , Jianwei Niu , Xuefeng Liu , Longhui Wei , Qi Tian

Extending the forecasting time is a critical demand for real applications, such as extreme weather early warning and long-term energy consumption planning. This paper studies the long-term forecasting problem of time series. Prior…

Machine Learning · Computer Science 2022-01-10 Haixu Wu , Jiehui Xu , Jianmin Wang , Mingsheng Long

The Transformer architecture has become a cornerstone of modern artificial intelligence, but its core self-attention mechanism suffers from a complexity bottleneck that scales quadratically with sequence length, severely limiting its…

Machine Learning · Computer Science 2025-08-29 Zhongpan Tang

Time-series forecasts are essential for planning and decision-making in many domains. Explainability is key to building user trust and meeting transparency requirements. Shapley Additive Explanations (SHAP) is a popular explainable AI…

Machine Learning · Computer Science 2025-12-24 Matthias Hertel , Sebastian Pütz , Ralf Mikut , Veit Hagenmeyer , Benjamin Schäfer

Transformer-based models have demonstrated remarkable in-context learning capabilities, prompting extensive research into its underlying mechanisms. Recent studies have suggested that Transformers can implement first-order optimization…

Machine Learning · Computer Science 2024-03-06 Angeliki Giannou , Liu Yang , Tianhao Wang , Dimitris Papailiopoulos , Jason D. Lee

Deep learning has achieved remarkable success in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers have largely replaced recurrent networks in these tasks.…

Machine Learning · Computer Science 2025-08-05 Ivan Karpukhin , Andrey Savchenko

Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling noise. Specifically, the differential attention mechanism…

Computation and Language · Computer Science 2025-04-08 Tianzhu Ye , Li Dong , Yuqing Xia , Yutao Sun , Yi Zhu , Gao Huang , Furu Wei

Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes…

Computation and Language · Computer Science 2023-11-30 Tong Xiao , Jingbo Zhu