mlsanityData to 14 Oct 2026

PyG 2.0: Scalable Learning on Real World Graphs

arXiv 2507.16991 ↗First posted 22 Jul 2025cs.LG cs.AIcited by 52

Not on the map. Why?

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.

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

57 of 93 references.

References · 57

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2017Graph Attention Networkscited by 8,923
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  9. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  11. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  12. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
38 more
  1. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  2. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  3. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  4. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  5. 2019Heterogeneous Graph Attention Networkcited by 734
  6. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  7. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  8. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  9. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  10. 2020Heterogeneous Graph Transformercited by 582
  11. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  12. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
  13. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  14. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  15. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
  16. 2020DeeperGCN: All You Need to Train Deeper GCNscited by 250
  17. 2022Pure Transformers are Powerful Graph Learnerscited by 188
  18. 2020ContactPose: A Dataset of Grasps with Object Contact and Hand Posecited by 183
  19. 2020Design Space for Graph Neural Networkscited by 182
  20. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  21. 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 161
  22. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  23. 2020Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphscited by 115
  24. 2021Combinatorial Optimization with Physics-Inspired Graph Neural Networkscited by 108
  25. 2024RelBench: A Benchmark for Deep Learning on Relational Databasescited by 96
  26. 2021GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddingscited by 90
  27. 2020Deep Graph Matching Consensuscited by 85
  28. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  29. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 49
  30. 2021Torch.fx: Practical Program Capture and Transformation for Deep Learning in Pythoncited by 40
  31. 2023Trompt: Towards a Better Deep Neural Network for Tabular Datacited by 36
  32. 2020Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisionscited by 34
  33. 2023ExcelFormer: A neural network surpassing GBDTs on tabular datacited by 34
  34. 2022PyGOD: A Python Library for Graph Outlier Detectioncited by 32
  35. 2024PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learningcited by 32
  36. 2023Graph-based Neural Weather Prediction for Limited Area Modelingcited by 22
  37. 2018Design Principles for Sparse Matrix Multiplication on the GPUcited by 19
  38. 2021Large-scale graph representation learning with very deep GNNs and self-supervisioncited by 18

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 41.

52 papers.

Sort:

By area:

  1. 2026Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databasescited by 8
  2. 2026GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysiscited by 6
  3. 2026GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operatorscited by 4
  4. 2025TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphscited by 3
  5. 2025Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extractioncited by 2
  6. 2025Bridging Code Graphs and Large Language Models for Better Code Understandingcited by 2
  7. 2025Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Modelscited by 2
  8. 2026Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encodingcited by 2
  9. 2026Super-resolution of turbulent reacting flows on complex meshes using graph neural networkscited by 2
  10. 2026Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysiscited by 2
  11. 2026Have Graph -- Will Lift? The Case for Higher-Order Benchmarkscited by 2
  12. 2025Database Views as Explanations for Relational Deep Learningcited by 1
38 more
  1. 2026FEM-Informed Hypergraph Neural Networks for Efficient Elastoplasticitycited by 1
  2. 2026OPBench: A Graph Benchmark to Combat the Opioid Crisiscited by 1
  3. 2026Boltzmann Generators for Condensed Matter via Riemannian Flow Matchingcited by 1
  4. 2026Implicit Regularization of Mini-Batch Training in Graph Neural Networkscited by 1
  5. 2026Graph Neural Networks Are Not Continuous Across Graph Resolutionscited by 1
  6. 2025Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Sizecited by 0
  7. 2025Learning Contact Dynamics through Touching: Action-conditional Graph Neural Networks for Robotic Peg Insertioncited by 0
  8. 2025CrediBench: Building Web-Scale Network Datasets for Information Integritycited by 0
  9. 2025Inductive inference of gradient-boosted decision trees on graphs for insurance fraud detectioncited by 0
  10. 2025Bounded Graph Clustering with Graph Neural Networkscited by 0
  11. 2025Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecastingcited by 0
  12. 2026Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEscited by 0
  13. 2026Plain Transformers are Surprisingly Powerful Link Predictorscited by 0
  14. 2026Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelinescited by 0
  15. 2026PowerModelsGAT-AI: Physics-Informed Graph Attention for Multi-System Power Flow with Continual Learningcited by 0
  16. 2026Modeling subgrid scale production rates on complex meshes using graph neural networkscited by 0
  17. 2026The Impact of Dimensionality on the Stability of Node Embeddingscited by 0
  18. 2026Fused Gromov-Wasserstein Distance with Feature Selectioncited by 0
  19. 2026Learning Minimally Rigid Graphs with High Realization Countscited by 0
  20. 2026Generating Physically Consistent Molecules with Energy-Based Modelscited by 0
  21. 2026Multitask learning with semiempirical orbital charges enables sample-efficient MLIPscited by 0
  22. 2026Evaluating passing decision-making in professional football: An enhanced MPNN approach to Receiver Selectioncited by 0
  23. 2026SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matchingcited by 0
  24. 2026On Efficient Scaling of GNNs via IO-Aware Layers Implementationscited by 0
  25. 2026STELLAR: Spatio-Temporal Environmental Learning with Latent Alignment and Refinement for Long-Tailed Species Distribution Modelingcited by 0
  26. 2026RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendationcited by 0
  27. 2026CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networkscited by 0
  28. 2026Pulmonary Embolism Risk Stratification from CTPA and Medical Records: Vascular Graphs Are Not All You Needcited by 0
  29. 2026GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based Modelscited by 0
  30. 2026Fully Inductive Cardinality Estimationcited by 0
  31. 2026Rethinking Learning-Based Influence Maximization: Simple Neural Surrogates and Native Discrete Searchcited by 0
  32. 2026Can Graph Learning Learn Circuits?cited by 0
  33. 2026Graph Machine Learning: An Opportunity for Power Systemscited by 0
  34. 2026MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selectioncited by 0
  35. 2026Learning to build covering structures with continuous adjustmentscited by 0
  36. 2026WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testingcited by 0
  37. 2026Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topographycited by 0
  38. 2026Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmarkcited by 0

50 most cited of 52 All 52 (JSON)