English
Related papers

Related papers: First De-Trend then Attend: Rethinking Attention f…

200 papers

To enhance the accuracy and robustness of PM$_{2.5}$ concentration forecasting, this paper introduces FALNet, a Frequency-Aware LSTM Network that integrates frequency-domain decomposition, temporal modeling, and attention-based refinement.…

Machine Learning · Computer Science 2025-04-16 Jiahui Lu , Shuang Wu , Zhenkai Qin , Guifang Yang

Various modifications of TRANSFORMER were recently used to solve time-series forecasting problem. We propose Query Selector - an efficient, deterministic algorithm for sparse attention matrix. Experiments show it achieves state-of-the art…

Machine Learning · Computer Science 2021-08-18 Jacek Klimek , Jakub Klimek , Witold Kraskiewicz , Mateusz Topolewski

The performance of time series forecasting has recently been greatly improved by the introduction of transformers. In this paper, we propose a general multi-scale framework that can be applied to the state-of-the-art transformer-based time…

Machine Learning · Computer Science 2023-02-08 Amin Shabani , Amir Abdi , Lili Meng , Tristan Sylvain

Today, the acquisition of various behavioral log data has enabled deeper understanding of customer preferences and future behaviors in the marketing field. In particular, multimodal deep learning has achieved highly accurate predictions by…

Computational Engineering, Finance, and Science · Computer Science 2024-05-14 Junichiro Niimi

We present a motion-adaptive temporal attention mechanism for parameter-efficient video generation built upon frozen Stable Diffusion models. Rather than treating all video content uniformly, our method dynamically adjusts temporal…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Rui Hong , Shuxue Quan

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong

Long-sequence video diffusion transformers hit a quadratic self-attention cost that dominates runtime and memory for very long token sequences. Most efficient attention methods use one approximation everywhere, yet video features are…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Haopeng Jin

Long-term time series forecasting (LTSF) is hampered by the challenge of modeling complex dependencies that span multiple temporal scales and frequency resolutions. Existing methods, including Transformer and MLP-based models, often…

Machine Learning · Computer Science 2025-09-22 Qianyang Li , Xingjun Zhang , Shaoxun Wang , Jia Wei

Recently, there has been a surge of Transformer-based solutions for the long-term time series forecasting (LTSF) task. Despite the growing performance over the past few years, we question the validity of this line of research in this work.…

Artificial Intelligence · Computer Science 2022-08-18 Ailing Zeng , Muxi Chen , Lei Zhang , Qiang Xu

This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation,…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Yifan Pu , Zhuofan Xia , Jiayi Guo , Dongchen Han , Qixiu Li , Duo Li , Yuhui Yuan , Ji Li , Yizeng Han , Shiji Song , Gao Huang , Xiu Li

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Christian Bohn , Thomas Kurbiel , Klaus Friedrichs , Hasan Tercan , Tobias Meisen

Transformers excel across domains, yet their quadratic attention complexity poses a barrier to scaling. Random-feature attention, as in Performers, can reduce this cost to linear in the sequence length by approximating the softmax kernel…

Machine Learning · Computer Science 2026-03-05 Amirhossein Farzam , Hossein Mobahi , Nolan Andrew Miller , Luke Sernau

Spatiotemporal predictive learning aims to generate future frames by learning from historical frames. In this paper, we investigate existing methods and present a general framework of spatiotemporal predictive learning, in which the spatial…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Cheng Tan , Zhangyang Gao , Lirong Wu , Yongjie Xu , Jun Xia , Siyuan Li , Stan Z. Li

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran

We present a theoretical analysis of the performance of transformer with softmax attention in in-context learning with linear regression tasks. While the existing literature predominantly focuses on the convergence of transformers with…

Machine Learning · Computer Science 2024-02-01 Yingqian Cui , Jie Ren , Pengfei He , Jiliang Tang , Yue Xing

We present a conformal prediction method for time series using the Transformer architecture to capture long-memory and long-range dependencies. Specifically, we use the Transformer decoder as a conditional quantile estimator to predict the…

Machine Learning · Computer Science 2024-06-11 Junghwan Lee , Chen Xu , Yao Xie

We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on…

Multivariate time series forecasting tasks are usually conducted in a channel-dependent (CD) way since it can incorporate more variable-relevant information. However, it may also involve a lot of irrelevant variables, and this even leads to…

Machine Learning · Computer Science 2024-05-15 Qinshuo Liu , Yanwen Fang , Pengtao Jiang , Guodong Li

Due to effective pattern mining and feature representation, neural forecasting models based on deep learning have achieved great progress. The premise of effective learning is to collect sufficient data. However, in time series forecasting,…

Machine Learning · Computer Science 2023-07-04 Yan Gao , Yan Wang , Qiang Wang

Multi-dimensional time series data, such as matrix and tensor-variate time series, are increasingly prevalent in fields such as economics, finance, and climate science. Traditional Transformer models, though adept with sequential data, do…

Machine Learning · Computer Science 2024-10-29 Linghang Kong , Elynn Chen , Yuzhou Chen , Yuefeng Han
‹ Prev 1 8 9 10 Next ›