English
Related papers

Related papers: Half-Hop: A graph upsampling approach for slowing …

200 papers

Message passing neural networks (MPNN) have seen a steep rise in popularity since their introduction as generalizations of convolutional neural networks to graph-structured data, and are now considered state-of-the-art tools for solving a…

Machine Learning · Computer Science 2022-08-05 Sohir Maskey , Ron Levie , Yunseok Lee , Gitta Kutyniok

Graph Neural Networks (GNNs) have achieved tremendous success in a variety of real-world applications by relying on the fixed graph data as input. However, the initial input graph might not be optimal in terms of specific downstream tasks,…

Machine Learning · Computer Science 2023-09-22 Beidi Zhao , Boxin Du , Zhe Xu , Liangyue Li , Hanghang Tong

Graph Neural Networks (GNNs) have demonstrated strong performance in graph mining tasks due to their message-passing mechanism, which is aligned with the homophily assumption that adjacent nodes exhibit similar behaviors. However, in many…

Machine Learning · Computer Science 2024-05-29 Zhuonan Zheng , Yuanchen Bei , Sheng Zhou , Yao Ma , Ming Gu , HongJia XU , Chengyu Lai , Jiawei Chen , Jiajun Bu

Traditional Graph Neural Networks (GNNs) rely on network homophily, which can lead to performance degradation due to over-smoothing in many real-world heterophily scenarios. Recent studies analyze the smoothing effect (separability) after…

Machine Learning · Computer Science 2024-11-05 Yoonhyuk Choi , Jiho Choi , Taewook Ko , Chong-Kwon Kim

Message passing is the core operation in graph neural networks, where each node updates its embeddings by aggregating information from its neighbors. However, in deep architectures, this process often leads to diminished expressiveness. A…

Machine Learning · Computer Science 2025-11-11 Mohammad Shirzadi , Ali Safarpoor Dehkordi , Ahad N. Zehmakan

Real-world graphs exhibit increasing heterophily, where nodes no longer tend to be connected to nodes with the same label, challenging the homophily assumption of classical graph neural networks (GNNs) and impeding their performance.…

Machine Learning · Computer Science 2024-08-22 Jiajun Zhou , Chenxuan Xie , Shengbo Gong , Jiaxu Qian , Shanqing Yu , Qi Xuan , Xiaoniu Yang

Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the…

Machine Learning · Computer Science 2019-10-29 Guangtao Wang , Rex Ying , Jing Huang , Jure Leskovec

Most Graph Neural Networks (GNNs) propagate messages by treating node embeddings as holistic feature vectors, implicitly assuming uniform relevance across feature dimensions. This limits their ability to selectively transmit informative…

Machine Learning · Computer Science 2025-12-24 Longlong Li , Mengyang Zhao , Guanghui Wang , Cunquan Qu

Matching local features across images is a fundamental problem in computer vision. Targeting towards high accuracy and efficiency, we propose Seeded Graph Matching Network, a graph neural network with sparse structure to reduce redundant…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Hongkai Chen , Zixin Luo , Jiahui Zhang , Lei Zhou , Xuyang Bai , Zeyu Hu , Chiew-Lan Tai , Long Quan

A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information…

Machine Learning · Computer Science 2020-03-25 Xinhan Di , Pengqian Yu , Rui Bu , Mingchao Sun

The computation of distance measures between nodes in graphs is inefficient and does not scale to large graphs. We explore dense vector representations as an effective way to approximate the same information: we introduce a simple yet…

Computation and Language · Computer Science 2019-06-18 Andrey Kutuzov , Mohammad Dorgham , Oleksiy Oliynyk , Chris Biemann , Alexander Panchenko

The message-passing paradigm of Graph Neural Networks often struggles with exchanging information across distant nodes typically due to structural bottlenecks in certain graph regions, a limitation known as \textit{over-squashing}. To…

Machine Learning · Computer Science 2025-06-23 Langzhang Liang , Fanchen Bu , Zixing Song , Zenglin Xu , Shirui Pan , Kijung Shin

Graph convolutional networks produce good predictions of unlabeled samples due to its transductive label propagation. Since samples have different predicted confidences, we take high-confidence predictions as pseudo labels to expand the…

Machine Learning · Computer Science 2020-09-07 Kun Zhan , Chaoxi Niu

Graph neural networks (GNNs) have received much attention recently because of their excellent performance on graph-based tasks. However, existing research on GNNs focuses on designing more effective models without considering much about the…

Machine Learning · Computer Science 2021-04-20 Han Yang , Xiao Yan , Xinyan Dai , Yongqiang Chen , James Cheng

Training deep graph neural networks (GNNs) poses a challenging task, as the performance of GNNs may suffer from the number of hidden message-passing layers. The literature has focused on the proposals of {over-smoothing} and…

Machine Learning · Statistics 2023-02-27 Yirui Liu , Xinghao Qiao , Liying Wang , Jessica Lam

As one of the most fundamental tasks in graph theory, subgraph matching is a crucial task in many fields, ranging from information retrieval, computer vision, biology, chemistry and natural language processing. Yet subgraph matching problem…

Machine Learning · Computer Science 2022-09-19 Zixun Lan , Limin Yu , Linglong Yuan , Zili Wu , Qiang Niu , Fei Ma

It is known that the current graph neural networks (GNNs) are difficult to make themselves deep due to the problem known as over-smoothing. Multi-scale GNNs are a promising approach for mitigating the over-smoothing problem. However, there…

Machine Learning · Computer Science 2021-01-07 Kenta Oono , Taiji Suzuki

Graph alignment, the problem of identifying corresponding nodes across multiple graphs, is fundamental to numerous applications. Most existing unsupervised methods embed node features into latent representations to enable cross-graph…

Machine Learning · Computer Science 2025-09-30 Maysam Behmanesh , Erkan Turan , Maks Ovsjanikov

Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks. Despite advancements of methodology based on deep learning in recent years, existing benchmarking approaches exhibit limitations that hinder…

Machine Learning · Computer Science 2024-03-08 Jing Gu , Dongmian Zou

Graph neural networks have been extensively studied for learning with inter-connected data. Despite this, recent evidence has revealed GNNs' deficiencies related to over-squashing, heterophily, handling long-range dependencies, edge…

Machine Learning · Computer Science 2023-06-16 Qitian Wu , Wentao Zhao , Zenan Li , David Wipf , Junchi Yan