Message Passing Graph Neural Network

Message Passing Graph Neural Networks (MPGNNs) are a class of neural networks designed to process graph-structured data by iteratively exchanging information between connected nodes. Current research focuses on improving their expressiveness, addressing limitations like over-squashing and over-smoothing, and enhancing efficiency through architectural innovations such as low-rank approximations and optimized aggregation methods. These advancements are significant because MPGNNs are increasingly used in diverse applications, from solving partial differential equations and power flow analysis to link prediction and node classification in complex networks, offering potential for significant improvements in speed and accuracy across various scientific and engineering domains.

Papers

October 29, 2024

Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning
Haitz Sáez de Ocáriz Borde, Artem Lukoianov, Anastasis Kratsios, Michael Bronstein, Xiaowen Dong
Human Attention Graph Representation Learning Graph Convolution Community Need Message Passing Message Passing Graph Neural Network

October 4, 2024

Improving Efficiency of Sampling-based Motion Planning via Message-Passing Monte Carlo
Makram Chahine, T. Konstantin Rusch, Zach J. Patterson, Daniela Rus
Motion Planning Monte Carlo Motion Planning Problem Message Passing Graph Neural Network Enhancing Efficiency Sampling Based Motion Planning Sampled Time Series

October 2, 2024

September 28, 2024

Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
Mitchell Keren Taraday, Almog David, Chaim Baskin
Message Passing Graph Neural Network Aware Aggregator

August 22, 2024

Enhanced Expressivity in Graph Neural Networks with Lanczos-Based Linear Constraints
Niloofar Azizi, Nils Kriege, Horst Bischof
Graph Neural Network Graph Structured Data Subgraph Structure Message Passing Graph Neural Network Linear Constraint Subgraph Extraction

July 5, 2024

Learning Geometric Invariant Features for Classification of Vector Polygons with Graph Message-passing Neural Network
Zexian Huang, Kourosh Khoshelham, Martin Tomko
Classification Code Graph Representation Geometric Feature Invariant Feature Message Passing Graph Neural Network Shape Classification

June 27, 2024

Improving the Expressiveness of $K$-hop Message-Passing GNNs by Injecting Contextualized Substructure Information
Tianjun Yao, Yiongxu Wang, Kun Zhang, Shangsong Liang
Graph Neural Network Gene Level GNN Message Passing Contextual Information Subgraph Structure Expressive Speech Message Passing Graph Neural Network Basin Hopping

June 13, 2024

Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
Yuankai Luo, Lei Shi, Xiao-Ming Wu
Graph Neural Network Graph Transformer Node Classification Strong Baseline Graph Machine Learning Message Passing Graph Neural Network

June 9, 2024

Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
Ziang Chen, Xiaohan Chen, Jialin Liu, Xinshang Wang, Wotao Yin
Graph Neural Network Neural Process Expressive Power Message Passing Graph Neural Network Nonlinear Programming Quadratic Programming Quadratic Program

May 29, 2024

Spatio-Spectral Graph Neural Networks
Simon Geisler, Arthur Kosmala, Daniel Herbst, Stephan Günnemann
Graph Neural Network Message Passing Graph Neural Network Spectral Graph Neural Network

May 27, 2024

Probabilistic Graph Rewiring via Virtual Nodes
Chendi Qian, Andrei Manolache, Christopher Morris, Mathias Niepert
Message Passing Message Passing Neural Network Message Passing Graph Neural Network Virtual Network Graph Rewiring Implicit Graph

April 6, 2024

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
Adarsh Jamadandi, Celia Rubio-Madrigal, Rebekka Burkholz
Message Passing Graph Neural Network Undisciplined Over Smoothing Squashing Mitigation Approach Spectral Gap

March 28, 2024

Tiny Graph Neural Networks for Radio Resource Management
Ahmad Ghasemi, Hossein Pishro-Nik
Neural Network Graph Neural Network Resource Allocation Message Passing Graph Neural Network Radio Resource Management

February 6, 2024

On dimensionality of feature vectors in MPNNs
César Bravo, Alexander Kozachinskiy, Cristóbal Rojas
Message Passing Data Dimensionality Message Passing Graph Neural Network Feature Vector Dimensional Feature Polynomial Activation

December 10, 2023

Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings
Nurudin Alvarez-Gonzalez, Andreas Kaltenbrunner, Vicenç Gómez
Graph Classification Large Relevance Improvement Message Passing Graph Neural Network Subgraph GNN Ego Network

December 7, 2023

Relational Deep Learning: Graph Representation Learning on Relational Databases
Matthias Fey, Weihua Hu, Kexin Huang, Jan Eric Lenssen, Rishabh Ranjan, Joshua Robinson, Rex Ying, Jiaxuan You, Jure Leskovec
Graph Representation Learning Graph Machine Learning Message Passing Graph Neural Network Relational Database Relational Deep Learning

November 13, 2023

Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges
Dai Shi, Andi Han, Lequan Lin, Yi Guo, Junbin Gao
New Benchmark Technical Challenge Gene Level GNN Right Problem Message Passing Neural Network Message Passing Graph Neural Network Current Method Graph Node Squashing Mitigation Approach Graph Level Learning

November 6, 2023

PowerFlowNet: Power Flow Approximation Using Message Passing Graph Neural Networks
Nan Lin, Stavros Orfanoudakis, Nathan Ordonez Cardenas, Juan S. Giraldo, Pedro P. Vergara
Power Grid Power System Message Passing Graph Neural Network Power Flow Power Network

October 16, 2023

Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems
Chendi Qian, Didier Chételat, Christopher Morris
Graph Neural Network Real Power Mixed Integer Linear Programming Message Passing Graph Neural Network

Message Passing Graph Neural Network

Papers

Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning

Improving Efficiency of Sampling-based Motion Planning via Message-Passing Monte Carlo

PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems

Rethinking the Expressiveness of GNNs: A Computational Model Perspective

Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks

Enhanced Expressivity in Graph Neural Networks with Lanczos-Based Linear Constraints

Learning Geometric Invariant Features for Classification of Vector Polygons with Graph Message-passing Neural Network

Improving the Expressiveness of $K$-hop Message-Passing GNNs by Injecting Contextualized Substructure Information

Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification

Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs

Spatio-Spectral Graph Neural Networks

Probabilistic Graph Rewiring via Virtual Nodes

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

Tiny Graph Neural Networks for Radio Resource Management

On dimensionality of feature vectors in MPNNs

Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings

Relational Deep Learning: Graph Representation Learning on Relational Databases

Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges

PowerFlowNet: Power Flow Approximation Using Message Passing Graph Neural Networks

Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems