# PyG 2.0: Scalable Learning on Real World Graphs

arXiv: https://arxiv.org/abs/2507.16991 · HTML: https://mlsanity.com/paper/2507.16991/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 93 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 30 of 57)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [DeeperGCN: All You Need to Train Deeper GCNs](https://mlsanity.com/paper/2006.07739/) (2020)
- [Pure Transformers are Powerful Graph Learners](https://mlsanity.com/paper/2207.02505/) (2022)
- [ContactPose: A Dataset of Grasps with Object Contact and Hand Pose](https://mlsanity.com/paper/2007.09545/) (2020)

## Built on by (most cited first, 30 of 52)

- [Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases](https://mlsanity.com/paper/2602.09572/) (2026)
- [GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis](https://mlsanity.com/paper/2608.09921/) (2026)
- [GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators](https://mlsanity.com/paper/2603.16849/) (2026)
- [TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2510.07586/) (2025)
- [Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction](https://mlsanity.com/paper/2509.22059/) (2025)
- [Bridging Code Graphs and Large Language Models for Better Code Understanding](https://mlsanity.com/paper/2512.07666/) (2025)
- [Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models](https://mlsanity.com/paper/2512.09514/) (2025)
- [Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding](https://mlsanity.com/paper/2602.13075/) (2026)
- [Super-resolution of turbulent reacting flows on complex meshes using graph neural networks](https://mlsanity.com/paper/2603.01080/) (2026)
- [Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis](https://mlsanity.com/paper/2604.20577/) (2026)
- [Have Graph -- Will Lift? The Case for Higher-Order Benchmarks](https://mlsanity.com/paper/2605.07397/) (2026)
- [Database Views as Explanations for Relational Deep Learning](https://mlsanity.com/paper/2509.09482/) (2025)
- [FEM-Informed Hypergraph Neural Networks for Efficient Elastoplasticity](https://mlsanity.com/paper/2602.07364/) (2026)
- [OPBench: A Graph Benchmark to Combat the Opioid Crisis](https://mlsanity.com/paper/2602.14602/) (2026)
- [Boltzmann Generators for Condensed Matter via Riemannian Flow Matching](https://mlsanity.com/paper/2602.18482/) (2026)
- [Implicit Regularization of Mini-Batch Training in Graph Neural Networks](https://mlsanity.com/paper/2605.22480/) (2026)
- [Graph Neural Networks Are Not Continuous Across Graph Resolutions](https://mlsanity.com/paper/2605.31315/) (2026)
- [Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size](https://mlsanity.com/paper/2509.01541/) (2025)
- [Learning Contact Dynamics through Touching: Action-conditional Graph Neural Networks for Robotic Peg Insertion](https://mlsanity.com/paper/2509.12151/) (2025)
- [CrediBench: Building Web-Scale Network Datasets for Information Integrity](https://mlsanity.com/paper/2509.23340/) (2025)
- [Inductive inference of gradient-boosted decision trees on graphs for insurance fraud detection](https://mlsanity.com/paper/2510.05676/) (2025)
- [Bounded Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2512.05623/) (2025)
- [Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting](https://mlsanity.com/paper/2512.22702/) (2025)
- [Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEs](https://mlsanity.com/paper/2601.11259/) (2026)
- [Plain Transformers are Surprisingly Powerful Link Predictors](https://mlsanity.com/paper/2602.01553/) (2026)
- [Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines](https://mlsanity.com/paper/2603.06952/) (2026)
- [PowerModelsGAT-AI: Physics-Informed Graph Attention for Multi-System Power Flow with Continual Learning](https://mlsanity.com/paper/2603.16879/) (2026)
- [Modeling subgrid scale production rates on complex meshes using graph neural networks](https://mlsanity.com/paper/2603.19841/) (2026)
- [The Impact of Dimensionality on the Stability of Node Embeddings](https://mlsanity.com/paper/2604.08492/) (2026)
- [Fused Gromov-Wasserstein Distance with Feature Selection](https://mlsanity.com/paper/2605.12161/) (2026)

## Abstract (arXiv)

PyG (PyTorch Geometric) has evolved significantly since its initial release, establishing itself as a leading framework for Graph Neural Networks. In this paper, we present Pyg 2.0 (and its subsequent minor versions), a comprehensive update that introduces substantial improvements in scalability and real-world application capabilities. We detail the framework's enhanced architecture, including support for heterogeneous and temporal graphs, scalable feature/graph stores, and various optimizations, enabling researchers and practitioners to tackle large-scale graph learning problems efficiently. Over the recent years, PyG has been supporting graph learning in a large variety of application areas, which we will summarize, while providing a deep dive into the important areas of relational deep learning and large language modeling.