Graph Isomorphism Network

Graph Isomorphism Networks (GINs) are a type of graph neural network designed to learn representations of graph-structured data that are invariant to node permutations, addressing limitations of other GNN architectures. Current research focuses on improving GIN efficiency and scalability for large graphs, enhancing their performance in various applications through modifications like weighted aggregators and incorporating techniques such as few-shot learning. GINs are proving valuable across diverse fields, including recommendation systems, topic modeling, matrix diagonalization, and grid reliability assessment, by offering improved accuracy and computational efficiency compared to traditional methods.

Papers

October 9, 2024

A Benchmark on Directed Graph Representation Learning in Hardware Designs
Haoyu Wang, Yinan Huang, Nan Wu, Pan Li
New Benchmark Graph Representation Learning Hardware Design Graph Isomorphism Network Hardware Platform

September 18, 2024

Edge-Based Graph Component Pooling
T. Snelleman, B.M. Renting, H.H. Hoos, J.N. van Rijn
Graph Neural Network Message Passing Geometric Deep Learning Sparse Graph Graph Pooling Graph Isomorphism Network

September 12, 2024

Enhancing Cross-Market Recommendation System with Graph Isomorphism Networks: A Novel Approach to Personalized User Experience
Sümeyye Öztürk, Ahmed Burak Ercan, Resul Tugay, Şule Gündüz Öğüdücü
Novel Approach Personalization Performance Traditional Recommender Graph Isomorphism Network Cross Market Recommendation

June 30, 2024

Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework
Geigh Zollicoffer, Kshitij Bhatta, Manish Bhattarai, Phil Romero, Christian F. A. Negre, Anders M. N. Niklasson, Adetokunbo Adedoyin
Large Matrix AlphaZero Based Artificial Intelligence Graph Isomorphism Network Matrix Diagonalization

April 2, 2024

GINopic: Topic Modeling with Graph Isomorphism Network
Suman Adhya, Debarshi Kumar Sanyal
Topic Modeling Topic Model Topic Analysis Graph Isomorphism Network Contextualized Language Model

February 5, 2024

Understanding and Guiding Weakly Supervised Entity Alignment with Potential Isomorphism Propagation
Yuanyi Wang, Wei Tang, Haifeng Sun, Zirui Zhuang, Xiaoyuan Fu, Jingyu Wang, Qi Qi, Jianxin Liao
Human Understanding Pairwise Similarity Graph Isomorphism Network Equivalent Entity Supervised Entity Alignment

December 4, 2023

On the Trade-Off between Stability and Representational Capacity in Graph Neural Networks
Zhan Gao, Amanda Prorok, Elvin Isufi
Graph Neural Network Core Stability Free Counterpart GNN Framework Representational Capacity Graph Isomorphism Network Graph Shift Operator Neural Network Weight Matrix

November 22, 2023

Benchmarking Toxic Molecule Classification using Graph Neural Networks and Few Shot Learning
Bhavya Mehta, Kush Kothari, Reshmika Nambiar, Seema Shrawne
Graph Neural Network Toxicity Detection Graph Isomorphism Network Toxicity Detection Datasets

October 2, 2023

Graph Isomorphic Networks for Assessing Reliability of the Medium-Voltage Grid
Charlotte Cambier van Nooten, Tom van de Poll, Sonja Füllhase, Jacco Heres, Tom Heskes, Yuliya Shapovalova
Power System Graph Isomorphism Network Power System Reliability

June 6, 2023

CIN++: Enhancing Topological Message Passing
Lorenzo Giusti, Teodora Reu, Francesco Ceccarelli, Cristian Bodnar, Pietro Liò
Graph Neural Network Molecular Property C++ Implementation Long Range Interaction Graph Isomorphism Network

May 24, 2023

HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification
He Zhu, Chong Zhang, Junjie Huang, Junran Wu, Ke Xu
Text Representation Hierarchical Text Classification Label Hierarchy Hierarchical Information Graph Isomorphism Network

February 9, 2023

Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
Haotian Ju, Dongyue Li, Aneesh Sharma, Hongyang R. Zhang
Graph Neural Network Strong Generalization Generalization Bound Generalization Gap Graph Diffusion Graph Level Classification Graph Isomorphism Network PAC Bayesian Bound Message Passing Network

July 3, 2022

A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition
Ying Hu, Yuwu Tang, Hao Huang, Liang He
Graph Neural Network Speech Emotion Recognition Aware Aggregator Graph Isomorphism Network

May 2, 2022

An improvement to a result about graph isomorphism networks using the prime factorization theorem
Rahul Sarkar
Large Relevance Improvement Key Result Prime Factorization Graph Isomorphism Network Finite Size Large Set

April 25, 2022

Completing Networks by Learning Local Connection Patterns
Zhang Zhang, Ruyi Tao, Yongzai Tao, Mingze Qi, Jiang Zhang
Link Prediction Graph Isomorphism Network Graph Auto

March 15, 2022

Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model
Xinjue Wang, Esa Ollila, Sergiy A. Vorobyov
Graph Neural Network Graph Convolutional Neural Network Graph Isomorphism Network Graph Shift Operator Error Model

January 31, 2022

MGNN: Graph Neural Networks Inspired by Distance Geometry Problem
Guanyu Cui, Zhewei Wei
Graph Neural Network Spatio Temporal Spectral Graph Neural Network Geometry Problem Graph Isomorphism Network

December 25, 2021

Task and Model Agnostic Adversarial Attack on Graph Neural Networks
Kartik Sharma, Samidha Verma, Sourav Medya, Arnab Bhattacharya, Sayan Ranu
Graph Neural Network Adversarial Attack Adversarial Perturbation Related Task GNN Model Graph Isomorphism Network Agnostic Adversarial

Graph Isomorphism Network

Papers

A Benchmark on Directed Graph Representation Learning in Hardware Designs

Edge-Based Graph Component Pooling

Enhancing Cross-Market Recommendation System with Graph Isomorphism Networks: A Novel Approach to Personalized User Experience

Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework

GINopic: Topic Modeling with Graph Isomorphism Network

Understanding and Guiding Weakly Supervised Entity Alignment with Potential Isomorphism Propagation

On the Trade-Off between Stability and Representational Capacity in Graph Neural Networks

Benchmarking Toxic Molecule Classification using Graph Neural Networks and Few Shot Learning

Graph Isomorphic Networks for Assessing Reliability of the Medium-Voltage Grid

CIN++: Enhancing Topological Message Passing

HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification

Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion

A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition

An improvement to a result about graph isomorphism networks using the prime factorization theorem

Completing Networks by Learning Local Connection Patterns

Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model

MGNN: Graph Neural Networks Inspired by Distance Geometry Problem

Task and Model Agnostic Adversarial Attack on Graph Neural Networks