English
Related papers

Related papers: Adaptive Multi-Neighborhood Attention based Transf…

200 papers

Linear attention mechanisms have emerged as efficient alternatives to full self-attention in Graph Transformers, offering linear time complexity. However, existing linear attention models often suffer from a significant drop in…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Zhaolin Hu , Kun Li , Hehe Fan , Yi Yang

Traffic forecasting is a fundamental problem in intelligent transportation systems. Existing traffic predictors are limited by their expressive power to model the complex spatial-temporal dependencies in traffic data, mainly due to the…

Machine Learning · Computer Science 2023-08-29 Adnan Zeb , Yongchao Ye , Shiyao Zhang , James J. Q. Yu

Transformer networks, driven by self-attention, are central to Large Language Models. In generative Transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, GPU-stored…

Neural and Evolutionary Computing · Computer Science 2024-11-26 Nathan Leroux , Paul-Philipp Manea , Chirag Sudarshan , Jan Finkbeiner , Sebastian Siegel , John Paul Strachan , Emre Neftci

Attention mechanisms underpin the computational power of Transformer models, which have achieved remarkable success across diverse domains. Yet understanding and extending the principles underlying self-attention remains a key challenge for…

Machine Learning · Computer Science 2025-11-14 Cheng Kevin Qu , Andrew Ly , Pulin Gong

Transformers have demonstrated remarkable performance across diverse domains. The key component of Transformers is self-attention, which learns the relationship between any two tokens in the input sequence. Recent studies have revealed that…

Machine Learning · Computer Science 2025-05-14 Hyowon Wi , Jeongwhan Choi , Noseong Park

Transformers achieve strong performance across diverse domains but implicitly assume Euclidean geometry in their attention mechanisms, limiting their effectiveness on data with non-Euclidean structure. While recent extensions to hyperbolic…

Machine Learning · Computer Science 2025-10-03 Ryan Y. Lin , Siddhartha Ojha , Nicholas Bai

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

Predicting interactions between structured entities lies at the core of numerous tasks such as drug regimen and new material design. In recent years, graph neural networks have become attractive. They represent structured entities as graphs…

Machine Learning · Computer Science 2020-04-21 Nuo Xu , Pinghui Wang , Long Chen , Jing Tao , Junzhou Zhao

Simulating physics using Graph Neural Networks (GNNs) is predominantly driven by message-passing architectures, which face challenges in scaling and efficiency, particularly in handling large, complex meshes. These architectures have…

Machine Learning · Computer Science 2025-08-26 Paul Garnier , Vincent Lannelongue , Jonathan Viquerat , Elie Hachem

Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further improve graph…

Machine Learning · Computer Science 2021-07-21 Xueting Han , Zhenhuan Huang , Bang An , Jing Bai

How can we enhance the node features acquired from Pretrained Models (PMs) to better suit downstream graph learning tasks? Graph Neural Networks (GNNs) have become the state-of-the-art approach for many high-impact, real-world graph…

Machine Learning · Computer Science 2025-04-01 Jing Zhu , Xiang Song , Vassilis N. Ioannidis , Danai Koutra , Christos Faloutsos

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is…

We present Adaptive Multi-layer Contrastive Graph Neural Networks (AMC-GNN), a self-supervised learning framework for Graph Neural Network, which learns feature representations of sample data without data labels. AMC-GNN generates two graph…

Machine Learning · Computer Science 2023-11-30 Shuhao Shi , Pengfei Xie , Xu Luo , Kai Qiao , Linyuan Wang , Jian Chen , Bin Yan

Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions and use fixed sharpness of attention coefficient distributions. This paper…

Machine Learning · Computer Science 2026-05-29 Zhongtian Ma , Hao Wu , Yexin Zhang , Qiaosheng Zhang , Zhen Wang

Graph neural networks (GNNs) have recently achieved state-of-the-art performance in many graph-based applications. Despite the high expressive power, they typically need to perform an expensive recursive neighborhood expansion in multiple…

Machine Learning · Computer Science 2022-06-10 Wentao Zhang , Ziqi Yin , Zeang Sheng , Wen Ouyang , Xiaosen Li , Yangyu Tao , Zhi Yang , Bin Cui

Graph Transformer (GT) recently has emerged as a new paradigm of graph learning algorithms, outperforming the previously popular Message Passing Neural Network (MPNN) on multiple benchmarks. Previous work (Kim et al., 2022) shows that with…

Machine Learning · Computer Science 2023-06-22 Chen Cai , Truong Son Hy , Rose Yu , Yusu Wang

Learning meaningful representations of free-hand sketches remains a challenging task given the signal sparsity and the high-level abstraction of sketches. Existing techniques have focused on exploiting either the static nature of sketches…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Peng Xu , Chaitanya K. Joshi , Xavier Bresson

Graph representation learning methods have been widely adopted in financial applications to enhance company representations by leveraging inter-firm relationships. However, current approaches face three key challenges: (1) The advantages of…

Statistical Finance · Quantitative Finance 2025-07-04 Yingjie Niu , Mingchuan Zhao , Valerio Poti , Ruihai Dong

We propose a generalization of transformer neural network architecture for arbitrary graphs. The original transformer was designed for Natural Language Processing (NLP), which operates on fully connected graphs representing all connections…

Machine Learning · Computer Science 2021-01-26 Vijay Prakash Dwivedi , Xavier Bresson

Unsupervised graph domain adaptation (UGDA) focuses on transferring knowledge from labeled source graph to unlabeled target graph under domain discrepancies. Most existing UGDA methods are designed to adapt information from a single source…

Machine Learning · Computer Science 2025-02-06 Zhen Zhang , Bingsheng He