English
Related papers

Related papers: Positional Encoding in Transformer-Based Time Seri…

200 papers

Time series forecasting is an important problem, with many real world applications. Ensembles of deep neural networks have recently achieved impressive forecasting accuracy, but such large ensembles are impractical in many real world…

Machine Learning · Computer Science 2022-08-31 Espen Haugsdal , Erlend Aune , Massimiliano Ruocco

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions…

Machine Learning · Computer Science 2024-06-05 Hongkang Li , Meng Wang , Tengfei Ma , Sijia Liu , Zaixi Zhang , Pin-Yu Chen

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

Several recent works use positional encodings to extend the receptive fields of graph neural network (GNN) layers equipped with attention mechanisms. These techniques, however, extend receptive fields to the complete graph, at substantial…

Machine Learning · Computer Science 2023-12-14 Rickard Brüel-Gabrielsson , Mikhail Yurochkin , Justin Solomon

Accurate vehicle trajectory prediction is crucial for ensuring safe and efficient autonomous driving. This work explores the integration of Transformer based model with Long Short-Term Memory (LSTM) based technique to enhance spatial and…

Robotics · Computer Science 2024-12-19 Chandra Raskoti , Weizi Li

It is well noted that coordinate based MLPs benefit -- in terms of preserving high-frequency information -- through the encoding of coordinate positions as an array of Fourier features. Hitherto, the rationale for the effectiveness of these…

Machine Learning · Computer Science 2021-10-13 Jianqiao Zheng , Sameera Ramasinghe , Simon Lucey

Time series forecasting is prevalent in extensive real-world applications, such as financial analysis and energy planning. Previous studies primarily focus on time series modality, endeavoring to capture the intricate variations and…

Machine Learning · Computer Science 2024-10-08 Jiaxiang Dong , Haixu Wu , Yuxuan Wang , Li Zhang , Jianmin Wang , Mingsheng Long

Sampling information using timing is a new approach in sampling theory. The question is how to map amplitude information into the timing domain. One such encoder, called time encoding machine, was introduced by Lazar and Toth in [23] for…

Information Theory · Computer Science 2013-07-02 David Gontier , Martin Vetterli

In this work, we propose a novel paradigm to encode the position of targets for target tracking in videos using transformers. The proposed paradigm, Dense Spatio-Temporal (DST) position encoding, encodes spatio-temporal position information…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Jinkun Cao , Hao Wu , Kris Kitani

In this paper, we propose an efficient transformer architecture that uses reinforced positional embedding to obtain superior performance with half the number of encoder decoder layers. We demonstrate that concatenating positional encoding…

Computation and Language · Computer Science 2024-10-08 Yen-Che Hsiao , Abhishek Dutta

Transformer-based visual object tracking has been utilized extensively. However, the Transformer structure is lack of enough inductive bias. In addition, only focusing on encoding the global feature does harm to modeling local details,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Changhong Fu , Weiyu Peng , Sihang Li , Junjie Ye , Ziang Cao

Without imposing prior distributional knowledge underlying multivariate time series of interest, we propose a nonparametric change-point detection approach to estimate the number of change points and their locations along the temporal axis.…

Methodology · Statistics 2021-05-13 Xiaodong Wang , Fushing Hsieh

Built upon the Transformer, large language models (LLMs) have captured worldwide attention due to their remarkable abilities. Nevertheless, all Transformer-based models including LLMs suffer from a preset length limit and can hardly…

Computation and Language · Computer Science 2024-10-08 Liang Zhao , Xiachong Feng , Xiaocheng Feng , Weihong Zhong , Dongliang Xu , Qing Yang , Hongtao Liu , Bing Qin , Ting Liu

Tokenization strategies shape how models process electronic health records, yet fair comparisons of their effectiveness remain limited. We present a systematic evaluation of tokenization approaches for clinical time series modeling using…

Machine Learning · Computer Science 2025-12-08 Rafi Al Attrach , Rajna Fani , David Restrepo , Yugang Jia , Peter Schüffler

Transformers with causal attention can solve tasks that require positional information without using positional encodings. In this work, we propose and investigate a new hypothesis about how positional information can be stored without…

Computation and Language · Computer Science 2025-01-03 Chunsheng Zuo , Pavel Guerzhoy , Michael Guerzhoy

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis

Position encoding is the primary mechanism which induces notion of sequential order for input tokens in transformer architectures. Even though this formulation in the original transformer paper has yielded plausible performance for general…

Computation and Language · Computer Science 2023-10-10 Eren Unlu

Transformer-based time series forecasting has recently gained strong interest due to the ability of transformers to model sequential data. Most of the state-of-the-art architectures exploit either temporal or inter-channel dependencies,…

Machine Learning · Computer Science 2025-03-25 Davide Villaboni , Alberto Castellini , Ivan Luciano Danesi , Alessandro Farinelli

In recent times, Large Language Models (LLMs) have captured a global spotlight and revolutionized the field of Natural Language Processing. One of the factors attributed to the effectiveness of LLMs is the model architecture used for…

Machine Learning · Computer Science 2023-08-31 Oluwaseyi Ogunfowora , Homayoun Najjaran

Transformer-based methods have achieved impressive results in time series forecasting. However, existing Transformers still exhibit limitations in sequence modeling as they tend to overemphasize temporal dependencies. This incurs additional…

Machine Learning · Computer Science 2025-12-16 Tan Wang , Yun Wei Dong , Qi Wang
‹ Prev 1 4 5 6 7 8 10 Next ›