English
Related papers

Related papers: Equipping Sketch Patches with Context-Aware Positi…

200 papers

Transformers are increasingly employed for graph data, demonstrating competitive performance in diverse tasks. To incorporate graph information into these models, it is essential to enhance node and edge features with positional encodings.…

Graph Network Simulators (GNSs) have emerged as powerful surrogates for complex physics-based simulation, offering inherent differentiability and orders-of-magnitude speedups over traditional solvers. However, GNSs typically assume access…

Positional embeddings (PE) play a crucial role in Vision Transformers (ViTs) by providing spatial information otherwise lost due to the permutation invariant nature of self attention. While absolute positional embeddings (APE) have shown…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Md Abtahi Majeed Chowdhury , Md Rifat Ur Rahman , Akil Ahmad Taki

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks…

Computation and Language · Computer Science 2026-05-29 Pierre-Antoine Lequeu , Camille Barboule , Benjamin Piwowarski

In this work, we propose novel families of positional encodings tailored to graph neural networks obtained with quantum computers. These encodings leverage the long-range correlations inherent in quantum systems that arise from mapping the…

Positional and structural encodings (PSE) enable better identifiability of nodes within a graph, rendering them essential tools for empowering modern GNNs, and in particular graph Transformers. However, designing PSEs that work optimally…

A current goal in the graph neural network literature is to enable transformers to operate on graph-structured data, given their success on language and vision tasks. Since the transformer's original sinusoidal positional encodings (PEs)…

Machine Learning · Computer Science 2023-04-11 Patrick Soga , David Chiang

Most existing graph neural networks (GNNs) learn node embeddings using the framework of message passing and aggregation. Such GNNs are incapable of learning relative positions between graph nodes within a graph. To empower GNNs with the…

Machine Learning · Computer Science 2024-11-05 Zhenyue Qin , Yiqun Zhang Saeed Anwar , Dongwoo Kim , Yang Liu , Pan Ji , Tom Gedeon

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

Majority of the existing graph neural networks (GNN) learn node embeddings that encode their local neighborhoods but not their positions. Consequently, two nodes that are vastly distant but located in similar local neighborhoods map to…

Social and Information Networks · Computer Science 2021-08-23 Sunil Nishad , Shubhangi Agarwal , Arnab Bhattacharya , Sayan Ranu

Designing effective positional encodings for graphs is key to building powerful graph transformers and enhancing message-passing graph neural networks. Although widespread, using Laplacian eigenvectors as positional encodings faces two…

Machine Learning · Computer Science 2024-06-11 Yinan Huang , William Lu , Joshua Robinson , Yu Yang , Muhan Zhang , Stefanie Jegelka , Pan Li

Spotting graphical symbols from the computer-aided design (CAD) drawings is essential to many industrial applications. Different from raster images, CAD drawings are vector graphics consisting of geometric primitives such as segments, arcs,…

Computer Vision and Pattern Recognition · Computer Science 2022-01-11 Zhaohua Zheng , Jianfang Li , Lingjie Zhu , Honghua Li , Frank Petzold , Ping Tan

Diffusion Transformers (DiTs) have emerged as the dominant architecture for visual generation, powering state-of-the-art image and video models. By representing images as patch tokens with positional encodings (PEs), DiTs combine…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Yunpeng Bai , Haoxiang Li , Qixing Huang

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by…

Computation and Language · Computer Science 2024-05-31 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar

Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction methods use a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Thomas Walker , Octave Mariotti , Amir Vaxman , Hakan Bilen

Recently, patch-wise contrastive learning is drawing attention for the image translation by exploring the semantic correspondence between the input and output images. To further explore the patch-wise topology for high-level semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-02-21 Chanyong Jung , Gihyun Kwon , Jong Chul Ye

Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments, etc.)…

Computer Vision and Pattern Recognition · Computer Science 2019-01-01 Anjan Dutta , Hichem Sahbi

Texture recognition is a fundamental problem in computer vision and pattern recognition. Recent progress leverages feature aggregation into discriminative descriptions based on convolutional neural networks (CNNs). However, modeling…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Bo Peng , Jintao Chen , Mufeng Yao , Chenhao Zhang , Jianghui Zhang , Mingmin Chi , Jiang Tao

Recognizing freehand sketches with high arbitrariness is greatly challenging. Most existing methods either ignore the geometric characteristics or treat sketches as handwritten characters with fixed structural ordering. Consequently, they…

Computer Vision and Pattern Recognition · Computer Science 2017-08-10 Qi Jia , Meiyu Yu , Xin Fan , Haojie Li

Positional encodings (PEs) are essential for effective graph representation learning because they provide position awareness in inherently position-agnostic transformer architectures and increase the expressive capacity of Graph Neural…

Machine Learning · Computer Science 2025-02-04 Charilaos I. Kanatsoulis , Evelyn Choi , Stephanie Jegelka , Jure Leskovec , Alejandro Ribeiro