English
Related papers

Related papers: Revisiting Graph Homophily Measures

200 papers

Graph drawings are commonly used to visualize relational data. User understanding and performance are linked to the quality of such drawings, which is measured by quality metrics. The tacit knowledge in the graph drawing community about…

Computational Geometry · Computer Science 2025-08-22 Simon van Wageningen , Tamara Mchedlidze , Alexandru C. Telea

Graph neural networks (GNNs) based methods have achieved impressive performance on node clustering task. However, they are designed on the homophilic assumption of graph and clustering on heterophilic graph is overlooked. Due to the lack of…

Social and Information Networks · Computer Science 2023-05-09 Erlin Pan , Zhao Kang

A new measure to assess the centrality of vertices in an undirected and connected graph is proposed. The proposed measure, L1 centrality, can adequately handle graphs with weights assigned to vertices and edges. The study provides tools for…

Methodology · Statistics 2024-04-23 Seungwoo Kang , Hee-Seok Oh

Graph Neural Networks (GNNs) have been highly successful for the node classification task. GNNs typically assume graphs are homophilic, i.e. neighboring nodes are likely to belong to the same class. However, a number of real-world graphs…

Machine Learning · Computer Science 2024-09-20 Yurui Lai , Taiyan Zhang , Rui Fan

A graph $H$ is said to be positive if the homomorphism density $t_H(G)$ is non-negative for all weighted graphs $G$. The positive graph conjecture proposes a characterisation of such graphs, saying that a graph is positive if and only if it…

Combinatorics · Mathematics 2024-04-29 David Conlon , Joonkyung Lee , Leo Versteegen

Many recent works have studied the performance of Graph Neural Networks (GNNs) in the context of graph homophily - a label-dependent measure of connectivity. Traditional GNNs generate node embeddings by aggregating information from a node's…

Machine Learning · Computer Science 2021-06-08 Hesham Mostafa , Marcel Nassar , Somdeb Majumdar

Graphs are used in almost every scientific discipline to express relations among a set of objects. Algorithms that compare graphs, and output a closeness score, or a correspondence among their nodes, are thus extremely important. Despite…

Discrete Mathematics · Computer Science 2020-11-17 Sam Safavi , José Bento

Graph Neural Networks (GNNs) have emerged as a powerful technique for learning on relational data. Owing to the relatively limited number of message passing steps they perform -- and hence a smaller receptive field -- there has been…

Machine Learning · Computer Science 2022-06-27 Ameya Velingker , Ali Kemal Sinop , Ira Ktena , Petar Veličković , Sreenivas Gollapudi

Assessing homophily in large-scale networks is central to understanding structural regularities in graphs, and thus inform the choice of models (such as graph neural networks) adopted to learn from network data. Evaluation of smoothness…

Signal Processing · Electrical Eng. & Systems 2025-12-22 Hamed Ajorlou , Gonzalo Mateos , Luana Ruiz

A signed graph is a graph together with an assignment of signs to the edges. A closed walk in a signed graph is said to be positive (negative) if it has an even (odd) number of negative edges, counting repetition. Recognizing the signs of…

Combinatorics · Mathematics 2021-06-16 Reza Naserasr , Eric Sopena , Thomas Zaslavsky

Homophily is the principle whereby "similarity breeds connections". We give a quantitative formulation of this principle within networks. Given a network and a labeled partition of its vertices, the vector indexed by each class of the…

Statistics Theory · Mathematics 2023-08-15 Nicola Apollonio , Paolo G. Franciosa , Daniele Santoni

This paper introduces a simple measure of a concordance pattern among observed outcomes along a network, i.e., the pattern in which adjacent outcomes tend to be more strongly correlated than non-adjacent outcomes. The graph concordance…

Methodology · Statistics 2017-09-04 Kyungchul Song

We introduce a homotopy theory of digraphs (directed graphs) and prove its basic properties, including the relations to the homology theory of digraphs constructed by the authors in previous papers. In particular, we prove the homotopy…

Algebraic Topology · Mathematics 2014-07-02 Alexander Grigor'yan , Yong Lin , Yuri Muranov , Shing-Tung Yau

We present a new metric of link cohesion for measuring the strength of edges in complex, highly connected graphs. Link cohesion accounts for local small hop connections and associated node degrees and can be used to support edge scoring and…

Social and Information Networks · Computer Science 2020-03-09 Cetin Savkli , Catherine Schwartz , Amanda Galante , Jonathan Cohen

Graph classification plays an important role is data mining, and various methods have been developed recently for classifying graphs. In this paper, we propose a novel method for graph classification that is based on homotopy equivalence of…

Discrete Mathematics · Computer Science 2017-07-18 Alexander V. Evako

Graph Neural Networks (GNNs) have achieved state-of-the-art results in node classification tasks. However, most improvements are in multi-class classification, with less focus on the cases where each node could have multiple labels. The…

Machine Learning · Computer Science 2024-06-19 Tianqi Zhao , Ngan Thi Dong , Alan Hanjalic , Megha Khosla

This paper proposes a simple procedure to decide whether the empirically-observed adjacency or weights matrix, which characterizes the graph underlying a socio-economic network, is sufficiently symmetric (respectively, asymmetric) to…

Physics and Society · Physics 2007-05-23 Giorgio Fagiolo

We study property testing of (di)graph properties in bounded-degree graph models. The study of graph properties in bounded-degree models is one of the focal directions of research in property testing in the last 15 years. However, despite…

Computational Complexity · Computer Science 2020-11-03 Hiro Ito , Areej Khoury , Ilan Newman

Graph embeddings, wherein the nodes of the graph are represented by points in a continuous space, are used in a broad range of Graph ML applications. The quality of such embeddings crucially depends on whether the geometry of the space…

Machine Learning · Statistics 2022-02-03 Francesco Di Giovanni , Giulia Luise , Michael Bronstein

Recently, graph neural networks (GNNs) have shown prominent performance in semi-supervised node classification by leveraging knowledge from the graph database. However, most existing GNNs follow the homophily assumption, where connected…

Machine Learning · Computer Science 2024-03-12 Henan Sun , Xunkai Li , Zhengyu Wu , Daohan Su , Rong-Hua Li , Guoren Wang
‹ Prev 1 3 4 5 6 7 10 Next ›