English
Related papers

Related papers: Learning to Encode Position for Transformer with C…

200 papers

Transformers are arguably the main workhorse in recent Natural Language Processing research. By definition a Transformer is invariant with respect to reordering of the input. However, language is inherently sequential and word order is…

Computation and Language · Computer Science 2021-09-10 Philipp Dufter , Martin Schmitt , Hinrich Schütze

Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study the memorization subtask from the point of view of the design…

Machine Learning · Computer Science 2020-02-03 Antonio Carta , Alessandro Sperduti , Davide Bacciu

We introduce Spline-based Transformers, a novel class of Transformer models that eliminate the need for positional encoding. Inspired by workflows using splines in computer animation, our Spline-based Transformers embed an input sequence of…

Machine Learning · Computer Science 2025-04-04 Prashanth Chandran , Agon Serifi , Markus Gross , Moritz Bächer

Learning deeper models is usually a simple and effective approach to improve model performance, but deeper models have larger model parameters and are more difficult to train. To get a deeper model, simply stacking more layers of the model…

Computation and Language · Computer Science 2021-08-27 GuoLiang Li , Yiyang Li

Cycles are fundamental elements in graph-structured data and have demonstrated their effectiveness in enhancing graph learning models. To encode such information into a graph learning framework, prior works often extract a summary quantity,…

Machine Learning · Computer Science 2023-12-01 Zuoyu Yan , Tengfei Ma , Liangcai Gao , Zhi Tang , Chao Chen , Yusu Wang

We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with another node using…

Machine Learning · Computer Science 2022-10-17 Wonpyo Park , Woonggi Chang , Donggeon Lee , Juntae Kim , Seung-won Hwang

Positional encodings are employed to capture the high frequency information of the encoded signals in implicit neural representation (INR). In this paper, we propose a novel positional encoding method which improves the reconstruction…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Bharath Bhushan Damodaran , Francois Schnitzler , Anne Lambert , Pierre Hellier

Deep sequence models typically degrade in accuracy when test sequences significantly exceed their training lengths, yet many critical tasks--such as algorithmic reasoning, multi-step arithmetic, and compositional generalization--require…

Machine Learning · Computer Science 2025-12-24 Philip Heejun Lee

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

We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches. Our framework provides a flexible mapping from the algebraic specification of a domain to an…

Machine Learning · Computer Science 2024-11-01 Konstantinos Kogkalidis , Jean-Philippe Bernardy , Vikas Garg

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

Neural Machine Translation model is a sequence-to-sequence converter based on neural networks. Existing models use recurrent neural networks to construct both the encoder and decoder modules. In alternative research, the recurrent networks…

Computation and Language · Computer Science 2021-05-04 Ritam Mallick , Seba Susan , Vaibhaw Agrawal , Rizul Garg , Prateek Rawal

The predominant approach for language modeling is to process sequences from left to right, but this eliminates a source of information: the order by which the sequence was generated. One strategy to recover this information is to decode…

Computation and Language · Computer Science 2021-11-01 Xuanlin Li , Brandon Trabucco , Dong Huk Park , Michael Luo , Sheng Shen , Trevor Darrell , Yang Gao

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness of position-based addressing. Many current methods enforce…

Computation and Language · Computer Science 2025-08-22 Jiajun Zhu , Peihao Wang , Ruisi Cai , Jason D. Lee , Pan Li , Zhangyang Wang

Modeling nonlinear spatiotemporal dynamical systems has primarily relied on partial differential equations (PDEs). However, the explicit formulation of PDEs for many underexplored processes, such as climate systems, biochemical reaction and…

Machine Learning · Computer Science 2023-05-23 Chengping Rao , Hao Sun , Yang Liu

Causal transformer language models (LMs), such as GPT-3, typically require some form of positional encoding, such as positional embeddings. However, we show that LMs without any explicit positional encoding are still competitive with…

Computation and Language · Computer Science 2022-12-07 Adi Haviv , Ori Ram , Ofir Press , Peter Izsak , Omer Levy

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

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

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