# Graph neural networks

Introduction to Graph Machine Learning, Everything is Connected: Graph Neural Networks & Attending to Graph Transformers are great reads.

DIG library is neat.

## Linksā

- A practical introduction to GNNs (2021)
- Spektral - Graph Neural Networks with Keras and Tensorflow 2. (Docs)
- A Comprehensive Survey on Graph Neural Networks (2019)
- Graph Neural Networks in TF2
- Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels (2019)
- Strategies for Pre-training Graph Neural Networks
- Transformers are Graph Neural Networks (2020) (HN)
- Towards understanding glasses with graph neural networks (2020)
- How Powerful are Graph Neural Networks?
- Resources for learning Graph Neural Networks for beginners (2020)
- Graph-based Deep Learning Literature
- PyTorch Cluster - PyTorch Extension Library of Optimized Graph Cluster Algorithms.
- Graph Neural Network Model in TensorFlow
- Traffic prediction with advanced Graph Neural Networks (2020) (HN)
- Transformers Are Graph Neural Networks (2020) (HN)
- Must-read papers on graph neural networks
- Latest developments in Graph Neural Networks: A list of recent conference talks (2020)
- DGL-LifeSci - Python package for graph neural networks in chemistry and biology.
- Introduction to Graph Neural Networks (2020)
- PyDGN - Python library for Deep Graph Networks.
- A gentle introduction to deep learning for graphs (2020)
- Graph Structure of Neural Networks - PyTorch implementation.
- GraphGym - Platform for designing and evaluating Graph Neural Networks.
- GraphRNN - Generating Realistic Graphs with Deep Auto-regressive Model.
- Position-aware Graph Neural Networks
- SEAL - Learning from Subgraphs, Embeddings, and Attributes for Link prediction
- Jraph - Lightweight library for working with graph neural networks in jax.
- Benchmarking Graph Neural Networks (2020) (Code)
- Pro-GNN - PyTorch implementation of "Graph Structure Learning for Robust Graph Neural Networks".
- Supervised Learning on Relational Databases with Graph Neural Networks
- Why Iām lukewarm on graph neural networks (2020) (HN)
- Simplicial Neural Networks - Generalization of graph neural networks to data that live on a class of topological spaces called [simplicial complexes].
- FLAG: Adversarial Data Augmentation for Graph Neural Networks
- Distilling Knowledge From Graph Convolutional Networks (2020) (Code)
- GN-Transformer AST - Code for "GN-Transformer: Fusing AST and Source Code information in Graph Networks" paper.
- Graph theory, graph convolutional networks, knowledge graphs (2021) (HN)
- Theoretical Foundations of Graph Neural Networks (2021)
- PyTorch GAT - PyTorch implementation of the original GAT paper.
- Graph Transformer Networks (2019) (Code)
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- DIG (Dive into Graphs) - Library for graph deep learning research.
- Understanding Graph Neural Networks from Graph Signal Denoising Perspectives (2020) (Code)
- Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions
- Graph Convolutional Networks in PyTorch
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges (2021)
- E(n) Equivariant Graph Neural Networks (2021) (Code)
- How Attentive are Graph Attention Networks? (2021) (Code)
- Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification (2021) (Code)
- Binary Graph Neural Networks (2021) (Code)
- Scaling Graph Neural Networks with Approximate PageRank (2020) (Code)
- CS224W: Machine Learning with Graphs (2021)
- Graph Attention Networks (GAT) annotated implementation
- Awesome Explainable Graph Reasoning - Collection of research papers and software related to explainability in graph machine learning.
- An Attempt at Demystifying Graph Deep Learning
- Graph Random Neural Network for Semi-Supervised Learning on Graphs (2020) (Code)
- CapsGNN: Capsule Graph Neural Networks in PyTorch
- A Gentle Introduction to Graph Neural Networks (2021)
- Understanding Convolutions on Graphs (2021)
- GraphNeuralNetworks.jl - Graph Neural Networks in Julia.
- MilaGraph - Research group focusing on graph representation learning and graph neural networks.
- Modeling Relational Data with Graph Convolutional Networks (2017) (Code)
- GNNLens2 - Visualization tool for Graph Neural Networks.
- Hierarchical Graph Representation Learning with Differentiable Pooling (2018) (Code)
- VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization (2021)
- Pitfalls of Graph Neural Network Evaluation (2019) (Code)
- Understanding Pooling in Graph Neural Networks (2021) (Code)
- Spectral Clustering with Graph Neural Networks for Graph Pooling (2020) (Code)
- Graph Robustness Benchmark (GRB) - Scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.
- TensorFlow GNN - Library to build Graph Neural Networks on the TensorFlow platform. (Article)
- Graph Neural Networks through the lens of Differential Geometry and Algebraic Topology (2021) (Tweet)
- DGN - Graph convolutional reinforcement learning, where the multi-agent environment is modeled as a graph, each agent is a node, and the encoding of local observation of agent is the feature of node.
- SE(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials (2021) (Tweet)
- On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features (2021) (Tweet)
- Graph Neural Networks as Neural Diffusion PDEs (2021)
- PyTorch Implementation and Explanation of Graph Representation Learning papers: DeepWalk, GCN, GraphSAGE, ChebNet & GAT
- Exact Combinatorial Optimization with Graph Convolutional Neural Networks (2021) (Code)
- A Recipe for Training Neural Networks (2019)
- GraphSAINT: Graph Sampling Based Inductive Learning Method (2020) (Code)
- Decoupling the Depth and Scope of Graph Neural Networks (2021) (Code)
- How to Scale Up GNNs with Mini-Batch Sampling (2021)
- Papers about explainability of GNNs
- GraphGallery - Gallery for benchmarking Graph Neural Networks (GNNs).
- From Canonical Correlation Analysis to Self-supervised Graph Neural Networks (2021) (Code)
- Expressive Power of Invariant and Equivariant Graph Neural Networks (2021) (Code)
- Simple implementation of Equivariant GNN in PyTorch
- GemNet: Universal Directional Graph Neural Networks for Molecules (2021) (Code)
- Graph4NLP - Easy-to-use library for R&D at the intersection of Deep Learning on Graphs and Natural Language Processing.
- GNNs Recipe - Recipe to study Graph Neural Networks (GNNs).
- GraphiT: Encoding Graph Structure in Transformers (2021) (Code)
- Graph Neural Networks with Learnable Structural and Positional Representations (2022) (Code)
- Deep Learning on Graphs Book
- Graph Neural Networks: Foundations, Frontiers, and Applications (2022)
- Representing Long-Range Context for Graph Neural Networks with Global Attention
- CW Networks - Message Passing Neural Networks for Simplicial and Cell Complexes.
- GMAN: A Graph Multi-Attention Network for Traffic Prediction
- Awesome Efficient Graph Neural Networks
- GraphSAGE - Inductive Representation Learning on Large Graphs. (PyTorch Code)
- Topological Graph Neural Networks (2022)
- Heterogeneous Graph Neural Network
- Graph Condensation for Graph Neural Networks (2022) (Code)
- Awesome Self Supervised GNN - Papers about pretraining and self-supervised learning on Graph Neural Networks (GNN).
- ptgnn - PyTorch Graph Neural Network Library.
- BrainGB - Unified, modular, scalable, and reproducible framework established for brain network analysis with GNNs. (Web)
- Equilibrium Aggregation (2022)
- Awesome resources on Graph Neural Networks
- Graph Neural Networks with convolutional ARMA filters (2021) (Code)
- Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation (2021) (Code)
- Geometric and Physical Quantities Improve E(3) Equivariant Message Passing (2021) (Code)
- Graph Attention Networks (2018) (Code)
- Directed Acyclic Graph Neural Networks (2022) (Code)
- Expressive GNNs and How To Tame Them (2022) (Tweet)
- Automated Self-Supervised Learning for Graphs (2022) (Code)
- Graph Neural PDEs
- Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs (2022) (Review)
- Sampling for Heterogeneous GNNs
- TensorFlow implementations of Graph Neural Networks
- gtrick - Bag of Tricks for Graph Neural Networks.
- How Airbnb is using Graph Convolutional Networks in production (2022)
- Foundations of Graph Neural Networks online course
- Basics of Graph Neural Networks
- Local Augmentation for Graph Neural Networks (2021) (Code)
- Awesome Expressive GNN
- Pure Transformers are Powerful Graph Learners (2022) (Code)
- Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs (2021) (Code)
- Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs (2020) (Code)
- M3GNet - Materials graph network with 3-body interactions featuring a DFT surrogate crystal relaxer and a state-of-the-art property predictor.
- Memory-Based Graph Networks (2020) (Code)
- Contrastive Multi-View Representation Learning on Graphs (2020) (Code)
- Tree Mover's Distance for Graphs: Bridging Graph Metrics and Stability of Graph Neural Networks (2022)
- SuperGlue: Learning Feature Matching with Graph Neural Networks (2020) (Code)
- Variational Graph Normalized Auto-Encoders (2021) (Code)
- GOOD: A Graph Out-of-Distribution Benchmark (2022)
- Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries (2022) (Code)
- Graph machine learning with missing node features (2022)
- PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images (2021) (Code)
- Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs (2022) (Code) (Code)
- Universal Graph Transformer Self-Attention Networks (2022)
- Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
- E3NN.jl - Julia implementation of Euclidean neural networks.
- GNN4Traffic - Collection of Graph Neural Network for Traffic Forecasting.
- Introduction to Graph Machine Learning (2023)
- Everything is Connected: Graph Neural Networks (2023)
- Graph Diffusion Convolution, as proposed in "Diffusion Improves Graph Learning" (2019)
- DiGress: Discrete Denoising diffusion models for graph generation (2023)
- Attending to Graph Transformers (2023) (Code)
- Awesome Graph Transformer
- Awesome Graph Neural Network Systems
- python_graphs - Static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.
- Gated Graph Sequence Neural Networks (2015) (Code)