Subgraph Counting

7 papers with code • 0 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Evaluating Graph Generative Models with Contrastively Learned Features

hamed1375/self-supervised-models-for-ggm-evaluation 13 Jun 2022

A wide range of models have been proposed for Graph Generative Models, necessitating effective methods to evaluate their quality.

Reinforcement Learning Enhanced Weighted Sampling for Accurate Subgraph Counting on Fully Dynamic Graph Streams

wangkaixin219/wsd 13 Nov 2022

Specifically, we propose a weighted sampling algorithm called WSD for estimating the subgraph count in a fully dynamic graph stream, which samples the edges based on their weights that indicate their importance and reflect their properties.

Improving Expressivity of Graph Neural Networks using Localization

roy-shubhajit/insig-gnn 31 May 2023

We focus on the specific problem of subgraph counting and give localized versions of $k-$WL for any $k$.

DeSCo: Towards Generalizable and Scalable Deep Subgraph Counting

fuvty/DeSCo 16 Aug 2023

We introduce DeSCo, a scalable neural deep subgraph counting pipeline, designed to accurately predict both the count and occurrence position of queries on target graphs post single training.

Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness

francesco-campi/rob-subgraphs 16 Aug 2023

We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs).

Communication Cost Reduction for Subgraph Counting under Local Differential Privacy via Hash Functions

gericko/grouprandomizedresponse 12 Dec 2023

We suggest the use of hash functions to cut down the communication costs when counting subgraphs under edge local differential privacy.

Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness

subgraph23/homomorphism-expressivity 16 Jan 2024

Specifically, we identify a fundamental expressivity measure termed homomorphism expressivity, which quantifies the ability of GNN models to count graphs under homomorphism.