Benchmarking Graph Neural Networks (2023-01-01T00:00:00.000000Z)

TL;DR

A reproducible GNN benchmarking framework is introduced, with the facility for researchers to add new models conveniently for arbitrary datasets, and a principled investigation into the recent Weisfeiler-Lehman GNNs (WL-GNNs) compared to message passing-based graph convolutional networks (GCNs).

Abstract

Graph neural networks (GNNs) have become the standard toolkit for analyzing and learning from data on graphs. As the field grows, it becomes critical to identify key architectures and validate new ideas that generalize to larger, more complex datasets. Unfortunately, it has been increasingly difficult to gauge the effectiveness of new models in the absence of a standardized benchmark with consistent experimental settings. In this paper, we introduce a reproducible GNN benchmarking framework, with the facility for researchers to add new models conveniently for arbitrary datasets. We demonstrate the usefulness of our framework by presenting a principled investigation into the recent Weisfeiler-Lehman GNNs (WL-GNNs) compared to message passing-based graph convolutional networks (GCNs) for a variety of graph tasks, i.e. graph regression/classification and node/link prediction, with medium-scale datasets.

Authors

Yoshua Bengio

69 papers

X. Bresson

7 papers

T. Laurent

4 papers

TL;DR

Abstract

Authors

References148 items

Transformers are Graph Neural Networks

Evaluating graph neural networks under graph sampling scenarios

Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks

GraphWorld: Fake Graphs Bring Real Insights for GNNs

Sign and Basis Invariant Networks for Spectral Graph Representation Learning

Graph Neural Networks with Learnable Structural and Positional Representations

Equivariant Subgraph Aggregation Networks

ETA Prediction with Graph Neural Networks in Google Maps

GraphiT: Encoding Graph Structure in Transformers

Do Transformers Really Perform Bad for Graph Representation?

Rethinking Graph Transformers with Spectral Attention

Do We Need Anisotropic Graph Neural Networks?

RAN-GNNs: Breaking the Capacity Limits of Graph Neural Networks

OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs

SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks

A pipeline for fair comparison of graph neural networks in node classification tasks

A Generalization of Transformer Networks to Graphs

Rethinking pooling in graph neural networks

Directional Graph Networks

Learning Graph Normalization for Graph Neural Networks

Distance Encoding -- Design Provably More Powerful GNNs for Structural Representation Learning

Degree-Quant: Quantization-Aware Training for Graph Neural Networks

Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks

Building powerful and equivariant graph neural networks with structural message-passing

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

Learning the travelling salesperson problem requires rethinking generalization

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

Open Graph Benchmark: Datasets for Machine Learning on Graphs

Low-Dimensional Hyperbolic Knowledge Graph Embeddings

SIGN: Scalable Inception Graph Neural Networks

Chip Placement with Deep Reinforcement Learning

Principal Neighbourhood Aggregation for Graph Nets

A Survey of Deep Learning for Scientific Discovery

Learning to Simulate Complex Physics with Graph Networks

Microsoft Academic Graph: When experts are not enough

A Gentle Introduction to Deep Learning for Graphs

A Fair Comparison of Graph Neural Networks for Graph Classification

Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning

PyTorch: An Imperative Style, High-Performance Deep Learning Library

The Deep Learning Revolution and Its Implications for Computer Architecture and Chip Design

DeepGCNs: Making GCNs Go as Deep as CNNs

On the Equivalence between Node Embeddings and Structural Graph Representations

Learning Symbolic Physics with Graph Networks

Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs

AqSolDB, a curated reference set of aqueous solubility and 2D descriptors for a diverse set of compounds

What graph neural networks cannot learn: depth vs width

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

Redundancy-Free Computation Graphs for Graph Neural Networks

A Two-Step Graph Convolutional Decoder for Molecule Generation

An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem

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

Provably Powerful Graph Networks

Position-aware Graph Neural Networks

Revisiting Graph Neural Networks: All We Have is Low-Pass Filters

Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

On Graph Classification Networks, Datasets and Baselines

Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification

SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems

Understanding Attention and Generalization in Graph Neural Networks

Self-Attention Graph Pooling

Relational Pooling for Graph Representations

Fast Graph Representation Learning with PyTorch Geometric

AliGraph: A Comprehensive Graph Neural Network Platform

Fake News Detection on Social Media using Geometric Deep Learning

On the Universality of Invariant Networks

Essential guidelines for computational method benchmarking

Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon

Pitfalls of Graph Neural Network Evaluation

Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks

Learning scheduling algorithms for data processing clusters

How Powerful are Graph Neural Networks?

Invariant and Equivariant Graph Networks

Capsule Graph Neural Network

Hierarchical Graph Representation Learning with Differentiable Pooling