English
Related papers

Related papers: Shape-aware Graph Spectral Learning

200 papers

Graph Neural Networks (GNNs) set the state-of-the-art in representation learning for graph-structured data. They are used in many domains, from online social networks to complex molecules. Most GNNs leverage the message-passing paradigm and…

Machine Learning · Computer Science 2025-03-06 Tuğrul Hasan Karabulut , İnci M. Baytaş

Machine learning frameworks such as graph neural networks typically rely on a given, fixed graph to exploit relational inductive biases and thus effectively learn from network data. However, when said graphs are (partially) unobserved,…

Machine Learning · Computer Science 2022-05-20 Max Wasserman , Saurabh Sihag , Gonzalo Mateos , Alejandro Ribeiro

Semi-supervised graph anomaly detection (GAD) utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. Current methods in this line posit that 1) normal nodes share a similar…

Machine Learning · Computer Science 2025-12-09 Guoguo Ai , Hezhe Qiao , Hui Yan , Guansong Pang

Graph Neural Networks (GNNs) typically operate by message-passing, where the state of a node is updated based on the information received from its neighbours. Most message-passing models act as graph convolutions, where features are mixed…

Graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings. First, they are essentially low-pass filters, thus the…

Machine Learning · Computer Science 2022-06-23 Zonghan Wu , Shirui Pan , Guodong Long , Jing Jiang , Chengqi Zhang

Spectral Graph Neural Networks effectively handle graphs with different homophily levels, with low-pass filter mining feature smoothness and high-pass filter capturing differences. When these distinct filters could naturally form two…

Machine Learning · Computer Science 2025-01-07 Ziyun Zou , Yinghui Jiang , Lian Shen , Juan Liu , Xiangrong Liu

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

Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications. However, most existing GNNs assume the graphs exhibit strong homophily in node labels, i.e., nodes with similar labels are…

Machine Learning · Computer Science 2023-02-20 Enyan Dai , Shijie Zhou , Zhimeng Guo , Suhang Wang

Graph neural networks (GNNs) use graph convolutions to exploit network invariances and learn meaningful feature representations from network data. However, on large-scale graphs convolutions incur in high computational cost, leading to…

Machine Learning · Computer Science 2022-06-29 Juan Cervino , Luana Ruiz , Alejandro Ribeiro

Over the last few years, we have witnessed the availability of an increasing data generated from non-Euclidean domains, which are usually represented as graphs with complex relationships, and Graph Neural Networks (GNN) have gained a high…

Machine Learning · Computer Science 2023-08-15 Andrea Apicella , Francesco Isgrò , Andrea Pollastro , Roberto Prevete

Graph Neural Networks (GNNs) struggle to balance heterophily and homophily in representation learning, a challenge further amplified in self-supervised settings. We propose H$^3$GNNs, an end-to-end self-supervised learning framework that…

Machine Learning · Computer Science 2025-04-17 Rui Xue , Tianfu Wu

Network data can be conveniently modeled as a graph signal, where data values are assigned to the nodes of a graph describing the underlying network topology. Successful learning from network data requires methods that effectively exploit…

Signal Processing · Electrical Eng. & Systems 2020-10-22 Samuel Pfrommer , Fernando Gama , Alejandro Ribeiro

Graph convolutional networks (GCNs) and its variants are designed for unsigned graphs containing only positive links. Many existing GCNs have been derived from the spectral domain analysis of signals lying over (unsigned) graphs and in each…

Machine Learning · Computer Science 2022-08-16 Rahul Singh , Yongxin Chen

Graph neural networks (GNNs) learn to represent nodes by aggregating information from their neighbors. As GNNs increase in depth, their receptive field grows exponentially, leading to high memory costs. Several existing methods address this…

Machine Learning · Computer Science 2025-07-16 Taraneh Younesian , Daniel Daza , Emile van Krieken , Thiviyan Thanapalasingam , Peter Bloem

Interpreting graph neural networks (GNNs) is difficult because message passing mixes signals and internal channels rarely align with human concepts. We study superposition, the sharing of directions by multiple features, directly in the…

Machine Learning · Computer Science 2026-01-19 Lukas Pertl , Han Xuanyuan , Pietro Liò

Due to the homophily assumption in graph convolution networks (GNNs), a common consensus in the graph node classification task is that GNNs perform well on homophilic graphs but may fail on heterophilic graphs with many inter-class edges.…

Machine Learning · Computer Science 2023-04-18 Jie Chen , Shouzhen Chen , Junbin Gao , Zengfeng Huang , Junping Zhang , Jian Pu

Graph neural networks (GNNs) have received tremendous attention due to their power in learning effective representations for graphs. Most GNNs follow a message-passing scheme where the node representations are updated by aggregating and…

Machine Learning · Computer Science 2021-05-11 Wei Jin , Xiaorui Liu , Yao Ma , Tyler Derr , Charu Aggarwal , Jiliang Tang

Graph Neural Networks (GNNs) have achieved great success but are often considered to be challenged by varying levels of homophily in graphs. Recent \textit{empirical} studies have surprisingly shown that homophilic GNNs can perform well…

Machine Learning · Computer Science 2025-10-27 Ming Gu , Zhuonan Zheng , Sheng Zhou , Meihan Liu , Jiawei Chen , Tanyu Qiao , Liangcheng Li , Jiajun Bu

With the rapid development of the World Wide Web (WWW), heterogeneous graphs (HG) have explosive growth. Recently, heterogeneous graph neural network (HGNN) has shown great potential in learning on HG. Current studies of HGNN mainly focus…

Social and Information Networks · Computer Science 2023-02-27 Jiayan Guo , Lun Du , Wendong Bi , Qiang Fu , Xiaojun Ma , Xu Chen , Shi Han , Dongmei Zhang , Yan Zhang

Graph neural networks (GNNs) often struggle to learn discriminative node representations for heterophilic graphs, where connected nodes tend to have dissimilar labels and feature similarity provides weak structural cues. We propose…

Machine Learning · Computer Science 2025-12-30 Ayushman Raghuvanshi , Gonzalo Mateos , Sundeep Prabhakar Chepuri