paper-with-me

Papers Isomorphism Testing

“Isomorphism Testing” 태그가 달린 논문 14편 · 필터 해제

Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization

2025-06-16 · Arie Soeteman, Balder ten Cate

We propose and study Hierarchical Ego Graph Neural Networks (HEGNNs), an expressive extension of graph neural networks (GNNs) with hierarchical node individualization, inspired by the Individualization-Refinement paradig…

Isomorphism Testing

Covered Forest: Fine-grained generalization analysis of graph neural networks

2024-12-10 · Antonis Vasileiou, Ben Finkelshtein, Floris Geerts, Ron Levie 외

The expressive power of message-passing graph neural networks (MPNNs) is reasonably well understood, primarily through combinatorial techniques from graph isomorphism testing. However, MPNNs' generalization abilities -- …

Graph SimilarityIsomorphism Testing

Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity

2023-08-18 · Van Thuy Hoang, O-Joun Lee

Graph representation learning (GRL) methods, such as graph neural networks and graph transformer models, have been successfully used to analyze graph-structured data, mainly focusing on node classification and link predi…

Graph ClassificationGraph Representation LearningIsomorphism TestingLink Prediction+4

PlanE: Representation Learning over Planar Graphs

2023-07-03 · NeurIPS 2023 11 · Radoslav Dimitrov, Zeyang Zhao, Ralph Abboud, İsmail İlkan Ceylan

Graph neural networks are prominent models for representation learning over graphs, where the idea is to iteratively compute representations of nodes of an input graph through a series of transformations in such a way th…

Isomorphism TestingRepresentation Learning

A Practical, Progressively-Expressive GNN

2022-10-18 · Lingxiao Zhao, Louis Härtel, Neil Shah, Leman Akoglu

Message passing neural networks (MPNNs) have become a dominant flavor of graph neural networks (GNNs) in recent years. Yet, MPNNs come with notable limitations; namely, they are at most as powerful as the 1-dimensional W…

Graph LearningIsomorphism Testing

Gradual Weisfeiler-Leman: Slow and Steady Wins the Race

2022-09-19 · Franka Bause, Nils M. Kriege

The classical Weisfeiler-Leman algorithm aka color refinement is fundamental for graph learning with kernels and neural networks. Originally developed for graph isomorphism testing, the algorithm iteratively refines vert…

Graph LearningIsomorphism Testing

Local Graph Embeddings Based on Neighbors Degree Frequency of Nodes

2022-07-30 · Vahid Shirbisheh

We propose a local-to-global strategy for graph machine learning and network analysis by defining certain local features and vector representations of nodes and then using them to learn globally defined metrics and prope…

Isomorphism Testing

Weisfeiler-Lehman meets Gromov-Wasserstein

2022-02-05 · Samantha Chen, Sunhyuk Lim, Facundo Mémoli, Zhengchao Wan 외

The Weisfeiler-Lehman (WL) test is a classical procedure for graph isomorphism testing. The WL test has also been widely used both for designing graph kernels and for analyzing graph neural networks. In this paper, we pr…

Isomorphism Testing

Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings

2022-01-31 · Or Feldman, Amit Boyarski, Shai Feldman, Dani Kogan 외

Graph isomorphism testing is usually approached via the comparison of graph invariants. Two popular alternatives that offer a good trade-off between expressive power and computational efficiency are combinatorial (i.e., …

Computational EfficiencyIsomorphism TestingOpen-Ended Question Answering

Graph Deformer Network

2021-01-01 · Wenting Zhao, Yuan Fang, Zhen Cui, Tong Zhang 외

Convolution learning on graphs draws increasing attention recently due to its potential applications to a large amount of irregular data. Most graph convolution methods leverage the plain summation/average aggregation to…

Isomorphism Testing

On Graph Neural Networks versus Graph-Augmented MLPs

2020-10-28 · ICLR 2021 1 · Lei Chen, Zhengdao Chen, Joan Bruna

From the perspective of expressive power, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which first augments nod…

Community DetectionIsomorphism Testing

Can Graph Neural Networks Count Substructures?

2020-02-10 · NeurIPS 2020 12 · Zhengdao Chen, Lei Chen, Soledad Villar, Joan Bruna

The ability to detect and count certain substructures in graphs is important for solving many tasks on graph-structured data, especially in the contexts of computational chemistry and biology as well as social network an…

Computational chemistryIsomorphism Testing

On the equivalence between graph isomorphism testing and function approximation with GNNs

2019-05-29 · NeurIPS 2019 12 · Zhengdao Chen, Soledad Villar, Lei Chen, Joan Bruna

Graph Neural Networks (GNNs) have achieved much success on graph-structured data. In light of this, there have been increasing interests in studying their expressive power. One line of work studies the capability of GNNs…

Graph RegressionIsomorphism Testing

Dimension Reduction via Colour Refinement

2013-07-22 · Martin Grohe, Kristian Kersting, Martin Mladenov, Erkal Selman

Colour refinement is a basic algorithmic routine for graph isomorphism testing, appearing as a subroutine in almost all practical isomorphism solvers. It partitions the vertices of a graph into "colour classes" in such a…

Dimensionality ReductionIsomorphism TestingMath
1–14 / 14