English
Related papers

Related papers: Resolving Node Identifiability in Graph Neural Pro…

200 papers

Positional encodings (PEs) are essential for building powerful and expressive graph neural networks and graph transformers, as they effectively capture the relative spatial relationships between nodes. Although extensive research has been…

Machine Learning · Computer Science 2026-03-16 Yinan Huang , Haoyu Wang , Pan Li

We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly…

Machine Learning · Computer Science 2019-08-08 Jiwoong Park , Minsik Lee , Hyung Jin Chang , Kyuewang Lee , Jin Young Choi

Graph neural networks are designed to learn functions on graphs. Typically, the relevant target functions are invariant with respect to actions by permutations. Therefore the design of some graph neural network architectures has been…

Machine Learning · Statistics 2022-11-03 Ningyuan Huang , Soledad Villar

The invariance to permutations of the adjacency matrix, i.e., graph isomorphism, is an overarching requirement for Graph Neural Networks (GNNs). Conventionally, this prerequisite can be satisfied by the invariant operations over node…

Machine Learning · Computer Science 2022-05-31 Zhongyu Huang , Yingheng Wang , Chaozhuo Li , Huiguang He

Line graph transformation has been widely studied in graph theory, where each node in a line graph corresponds to an edge in the original graph. This has inspired a series of graph neural networks (GNNs) applied to transformed line graphs,…

Machine Learning · Computer Science 2025-03-21 Fan Yang , Xingyue Huang

Comparison among graphs is ubiquitous in graph analytics. However, it is a hard task in terms of the expressiveness of the employed similarity measure and the efficiency of its computation. Ideally, graph comparison should be invariant to…

Social and Information Networks · Computer Science 2018-05-30 Anton Tsitsulin , Davide Mottin , Panagiotis Karras , Alex Bronstein , Emmanuel Müller

Today we have a good theoretical understanding of the representational power of Graph Neural Networks (GNNs). For example, their limitations have been characterized in relation to a hierarchy of Weisfeiler-Lehman (WL) isomorphism tests.…

Machine Learning · Computer Science 2023-03-08 Mohammad Sadegh Akhondzadeh , Vijay Lingam , Aleksandar Bojchevski

Graph kernels based on the $1$-dimensional Weisfeiler-Leman algorithm and corresponding neural architectures recently emerged as powerful tools for (supervised) learning with graphs. However, due to the purely local nature of the…

Data Structures and Algorithms · Computer Science 2020-10-20 Christopher Morris , Gaurav Rattan , Petra Mutzel

Identifying similar network structures is key to capture graph isomorphisms and learn representations that exploit structural information encoded in graph data. This work shows that ego-networks can produce a structural encoding scheme for…

Machine Learning · Computer Science 2022-12-09 Nurudin Alvarez-Gonzalez , Andreas Kaltenbrunner , Vicenç Gómez

Graph data widely exist in many high-impact applications. Inspired by the success of deep learning in grid-structured data, graph neural network models have been proposed to learn powerful node-level or graph-level representation. However,…

Machine Learning · Computer Science 2019-06-07 Jun Wu , Jingrui He , Jiejun Xu

Given a pair of graphs $\textbf{A}$ and $\textbf{B}$, the problems of deciding whether there exists either a homomorphism or an isomorphism from $\textbf{A}$ to $\textbf{B}$ have received a lot of attention. While graph homomorphism is…

Data Structures and Algorithms · Computer Science 2021-07-08 Silvia Butti , Victor Dalmau

While lifting map has significantly enhanced the expressivity of graph neural networks, extending this paradigm to hypergraphs remains fragmented. To address this, we introduce the categorical Weisfeiler-Lehman framework, which formalizes…

Machine Learning · Computer Science 2026-02-09 Seongjin Choi , Gahee Kim , Se-Young Yun

We provide a criterion to distinguish two graphs which are indistinguishable by $2$-dimensional Weisfeiler-Lehman algorithm for almost all graphs. Haemers conjectured that almost all graphs are identified by their spectrum. Our approach…

Combinatorics · Mathematics 2025-11-21 Wei Wang , Da Zhao

Graph neural networks (GNNs) have shown great success in learning from graph-based data. The key mechanism of current GNNs is message passing, where a node's feature is updated based on the information passing from its local neighbourhood.…

Machine Learning · Computer Science 2024-05-09 Yongze Wang , Haimin Zhang , Qiang Wu , Min Xu

Spectral approaches of network analysis heavily rely upon the eigendecomposition of the graph Laplacian. For instance, in graph signal processing, the Laplacian eigendecomposition is used to define the graph Fourier transform and then…

Machine Learning · Computer Science 2017-08-21 Dimitri Van De Ville , Robin Demesmaeker , Maria Giulia Preti

Graph-structured data is central to many scientific and industrial domains, where the goal is often to optimize objectives defined over graph structures. Given the combinatorial complexity of graph spaces, such optimization problems are…

Optimization and Control · Mathematics 2025-09-25 Shiqiang Zhang , Ruth Misener

Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressive power of graph neural networks (GNN). It was shown that the popular message passing GNN cannot distinguish between graphs that are…

Machine Learning · Computer Science 2020-06-11 Haggai Maron , Heli Ben-Hamu , Hadar Serviansky , Yaron Lipman

Graph self-supervised learning seeks to learn effective graph representations without relying on labeled data. Among various approaches, graph autoencoders (GAEs) have gained significant attention for their efficiency and scalability.…

Machine Learning · Computer Science 2025-06-17 Yang Liu , Deyu Bo , Wenxuan Cao , Yuan Fang , Yawen Li , Chuan Shi

In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods do not learn representations that can be interpreted in a straightforward…

Machine Learning · Computer Science 2021-01-05 Effrosyni Simou , Dorina Thanou , Pascal Frossard

The majority of popular graph kernels is based on the concept of Haussler's $\mathcal{R}$-convolution kernel and defines graph similarities in terms of mutual substructures. In this work, we enrich these similarity measures by considering…

Machine Learning · Computer Science 2021-10-25 Till Hendrik Schulz , Pascal Welke , Stefan Wrobel