English
Related papers

Related papers: Improving Transformers using Faithful Positional E…

200 papers

This paper introduces a novel approach to position embeddings in transformer models, named "Exact Positional Embeddings" (ExPE). An absolute positional embedding method that can extrapolate to sequences of lengths longer than the ones it…

Computation and Language · Computer Science 2025-10-06 Aleksis Datseris , Sylvia Vassileva , Ivan Koychev , Svetla Boytcheva

Understanding spatial location and relationships is a fundamental capability for modern artificial intelligence systems. Insights from human spatial cognition provide valuable guidance in this domain. Neuroscientific discoveries have…

Neural and Evolutionary Computing · Computer Science 2024-09-17 Boyang Li , Yulin Wu , Nuoxian Huang , Wenjia Zhang

Transformer-based methods have shown great potential in long-term time series forecasting. However, most of these methods adopt the standard point-wise self-attention mechanism, which not only becomes intractable for long-term forecasting…

Machine Learning · Computer Science 2022-02-24 Dazhao Du , Bing Su , Zhewei Wei

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

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

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

Machine learning has become a promising approach for molecular modeling. Positional quantities, such as interatomic distances and bond angles, play a crucial role in molecule physics. The existing works rely on careful manual design of…

Machine Learning · Computer Science 2022-11-24 Xiang Gao , Weihao Gao , Wenzhi Xiao , Zhirui Wang , Chong Wang , Liang Xiang

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism is position agnostic. In order to capture positional…

Computation and Language · Computer Science 2021-09-28 Zhiheng Huang , Davis Liang , Peng Xu , Bing Xiang

In the manufacturing process, sensor data collected from equipment is crucial for building predictive models to manage processes and improve productivity. However, in the field, it is challenging to gather sufficient data to build robust…

Machine Learning · Computer Science 2024-07-10 Gyeong Taek Lee , Oh-Ran Kwon

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

Since self-attention layers in Transformers are permutation invariant by design, positional encodings must be explicitly incorporated to enable spatial understanding. However, fixed-size lookup tables used in traditional learnable position…

Machine Learning · Computer Science 2025-06-18 Huayang Li , Yahui Liu , Hongyu Sun , Deng Cai , Leyang Cui , Wei Bi , Peilin Zhao , Taro Watanabe

In machine learning, effective modeling requires a holistic consideration of how to encode inputs, make predictions (i.e., decoding), and train the model. However, in time-series forecasting, prior work has predominantly focused on encoder…

Machine Learning · Computer Science 2025-12-30 Jaebin Lee , Hankook Lee

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

Financial prediction is a complex and challenging task of time series analysis and signal processing, expected to model both short-term fluctuations and long-term temporal dependencies. Transformers have remarkable success mostly in natural…

Machine Learning · Computer Science 2025-11-17 Nguyen Kim Hai Bui , Nguyen Duy Chien , Péter Kovács , Gergő Bognár

In this paper, we present a novel transformer-based architecture for end-to-end image compression. Our architecture incorporates blocks that effectively capture local dependencies between tokens, eliminating the need for positional encoding…

Image and Video Processing · Electrical Eng. & Systems 2024-09-09 Bouzid Arezki , Fangchen Feng , Anissa Mokraoui

The task of learning to map an input set onto a permuted sequence of its elements is challenging for neural networks. Set-to-sequence problems occur in natural language processing, computer vision and structure prediction, where…

Machine Learning · Computer Science 2022-06-09 Mateusz Jurewicz , Leon Derczynski

Although Transformer-based methods have significantly improved state-of-the-art results for long-term series forecasting, they are not only computationally expensive but more importantly, are unable to capture the global view of time series…

Machine Learning · Computer Science 2022-06-17 Tian Zhou , Ziqing Ma , Qingsong Wen , Xue Wang , Liang Sun , Rong Jin

One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules. Previous works build entropy models upon…

Image and Video Processing · Electrical Eng. & Systems 2023-03-16 Yichen Qian , Ming Lin , Xiuyu Sun , Zhiyu Tan , Rong Jin

We study the use of a time series encoder to learn representations that are useful on data set types with which it has not been trained on. The encoder is formed of a convolutional neural network whose temporal output is summarized by a…

Machine Learning · Computer Science 2018-05-11 Joan Serrà , Santiago Pascual , Alexandros Karatzoglou

Multivariate long-term time series forecasting is of great application across many domains, such as energy consumption and weather forecasting. With the development of transformer-based methods, the performance of multivariate long-term…

Machine Learning · Computer Science 2023-05-29 Zheng Sun , Yi Wei , Wenxiao Jia , Long Yu