English
Related papers

Related papers: Impact of Positional Encoding: Clean and Adversari…

200 papers

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

Numerous studies have demonstrated that the Transformer architecture possesses the capability for in-context learning (ICL). In scenarios involving function approximation, context can serve as a control parameter for the model, endowing it…

Machine Learning · Computer Science 2025-11-11 Qian Ma , Ruoxiang Xu , Yongqiang Cai

The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of positional encoding:…

Machine Learning · Computer Science 2024-08-26 Mitchell Black , Zhengchao Wan , Gal Mishne , Amir Nayyeri , Yusu Wang

In this work, we theoretically demonstrate that current graph positional encodings (PEs) are not beneficial and could potentially hurt performance in tasks involving heterophilous graphs, where nodes that are close tend to have different…

Machine Learning · Computer Science 2025-04-30 Michael Ito , Jiong Zhu , Dexiong Chen , Danai Koutra , Jenna Wiens

Positional encodings (PEs) are essential for building powerful and expressive graph neural networks and graph transformers, as they effectively capture the relative spatial relationships between nodes. Although extensive research has been…

Machine Learning · Computer Science 2026-03-16 Yinan Huang , Haoyu Wang , Pan Li

Positional encoding is essential for supplementing transformer with positional information of tokens. Existing positional encoding methods demand predefined token/feature order, rendering them unsuitable for real-world data with…

Machine Learning · Computer Science 2025-09-25 Kaichen Xu , Yihang Du , Mianpeng Liu , Zimu Yu , Xiaobo Sun

Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to…

Computation and Language · Computer Science 2024-05-29 Jie Wang , Tao Ji , Yuanbin Wu , Hang Yan , Tao Gui , Qi Zhang , Xuanjing Huang , Xiaoling Wang

Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that encodes relative positions through fixed, block-diagonal,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Sophie Ostmeier , Brian Axelrod , Maya Varma , Michael E. Moseley , Akshay Chaudhari , Curtis Langlotz

Characterizing the express power of the Transformer architecture is critical to understanding its capacity limits and scaling law. Recent works provide the circuit complexity bounds to Transformer-like architecture. On the other hand,…

Machine Learning · Computer Science 2024-12-03 Bo Chen , Xiaoyu Li , Yingyu Liang , Jiangxuan Long , Zhenmei Shi , Zhao Song

Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various…

Computation and Language · Computer Science 2023-11-09 Jianlin Su , Yu Lu , Shengfeng Pan , Ahmed Murtadha , Bo Wen , Yunfeng Liu

Positional encoding plays a crucial role in transformers, significantly impacting model performance and length generalization. Prior research has introduced absolute positional encoding (APE) and relative positional encoding (RPE) to…

Computation and Language · Computer Science 2024-11-06 Chuanyang Zheng , Yihang Gao , Han Shi , Minbin Huang , Jingyao Li , Jing Xiong , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

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

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…

Despite the success of Transformers on language understanding, code generation, and logical reasoning, they still fail to generalize over length on basic arithmetic tasks such as addition and multiplication. A major reason behind this…

Machine Learning · Computer Science 2024-06-05 Mahdi Sabbaghi , George Pappas , Hamed Hassani , Surbhi Goel

There are several improvements proposed over the baseline Absolute Positional Encoding (APE) method used in original transformer. In this study, we aim to investigate the implications of inadequately representing positional encoding in…

Computation and Language · Computer Science 2024-05-09 Arpit Aggarwal

Recently, Transformers for graph representation learning have become increasingly popular, achieving state-of-the-art performance on a wide-variety of graph datasets, either alone or in combination with message-passing graph neural networks…

Machine Learning · Computer Science 2024-05-07 Ayush Garg

How discriminative position information is for image classification depends on the data. On the one hand, the camera position is arbitrary and objects can appear anywhere in the image, arguing for translation invariance. At the same time,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Robert-Jan Bruintjes , Jan van Gemert

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

Graph Transformers (GTs) facilitate the comprehension of graph-structured data by calculating the self-attention of node pairs without considering node position information. To address this limitation, we introduce an innovative and…

Machine Learning · Computer Science 2023-12-12 Kushal Bose , Swagatam Das

Many machine learning models are vulnerable to adversarial attacks; for example, adding adversarial perturbations that are imperceptible to humans can often make machine learning models produce wrong predictions with high confidence.…

Machine Learning · Computer Science 2020-07-30 Dong Yin , Kannan Ramchandran , Peter Bartlett