paper-with-me

Papers

Graph Homomorphism Convolution

2020-05-03 · ICML 2020 1 · Hoang NT, Takanori Maehara

In this paper, we study the graph classification problem from the graph homomorphism perspective. We consider the homomorphisms from $F$ to $G$, where $G$ is a graph of interest (e.g. molecules or social networks) and $F$ belongs to some family of graphs (e.g. paths or non-isomorphic trees). We show that graph homomorphism numbers provide a natural invariant (isomorphism invariant and $\mathcal{F}$-invariant) embedding maps which can be used for graph classification. Viewing the expressive power of a graph classifier by the $\mathcal{F}$-indistinguishable concept, we prove the universality property of graph homomorphism vectors in approximating $\mathcal{F}$-invariant functions. In practice, by choosing $\mathcal{F}$ whose elements have bounded tree-width, we show that the homomorphism method is efficient compared with other methods.

📄 PDF Abstract BibTeX arXiv:2005.01214

Code (1)

gear/graph-homomorphism-network pytorch

Tasks

General ClassificationGraph Classification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Scaling up graph homomorphism for classification via sampling

2021-04-08 · Paul Beaujean, Florian Sikora, Florian Yger

Feature generation is an open topic of investigation in graph machine learning. In this paper, we study the use of graph homomorphism density features as a scalable alternative to homomorphism numbers which retain simila…

BIG-bench Machine LearningClassificationGeneral ClassificationGraph Classification+1

Algebraic Neural Networks: Stability to Deformations

2020-09-03 · Alejandro Parada-Mayorga, Alejandro Ribeiro

We study algebraic neural networks (AlgNNs) with commutative algebras which unify diverse architectures such as Euclidean convolutional neural networks, graph neural networks, and group neural networks under the umbrella…

Scaling Up Graph Homomorphism Features with Efficient Data Structures

2021-03-08 · ICLR Workshop GTRL 2021 5 · Paul Beaujean, Florian Sikora, Florian Yger

Typical datasets used in graph classification tasks only contain a few thousand graphs which rarely exceed hundreds of nodes. Graph homomorphism densities are permutation-invariant features that can be directly computed …

Graph Classification

Sampling random graph homomorphisms and applications to network data analysis

2019-10-21 · Hanbaek Lyu, Facundo Memoli, David Sivakoff

A graph homomorphism is a map between two graphs that preserves adjacency relations. We consider the problem of sampling a random graph homomorphism from a graph into a large network. We propose two complementary MCMC al…

Clustering

Improving Subgraph Matching by Combining Algorithms and Graph Neural Networks

2025-07-27 · Shuyang Guo, Wenjin Xie, Ping Lu, Ting Deng 외 arxiv

Homomorphism is a key mapping technique between graphs that preserves their structure. Given a graph and a pattern, the subgraph homomorphism problem involves finding a mapping from the pattern to the graph, ensuring tha…

Graph Neural Network