A geometry-aware multi-support heterogeneous GNN fuses point, line, and grid rainfall observations via cross-support message passing to reconstruct fields at arbitrary resolutions, reducing RMSE by 23.2% over baselines on Singapore data.
hub Mixed citations
Fast Graph Representation Learning with PyTorch Geometric
Mixed citation behavior. Most common role is background (40%).
71
Pith papers citing it
Background
40% of classified citations
abstract
We introduce PyTorch Geometric, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch. In addition to general graph data structures and processing methods, it contains a variety of recently published methods from the domains of relational learning and 3D data processing. PyTorch Geometric achieves high data throughput by leveraging sparse GPU acceleration, by providing dedicated CUDA kernels and by introducing efficient mini-batch handling for input examples of different size. In this work, we present the library in detail and perform a comprehensive comparative study of the implemented methods in homogeneous evaluation scenarios.
hub tools
citation-role summary
background 5
method 4
dataset 1
citation-polarity summary
representative citing papers
GNN-LaSDI combines graph autoencoders with latent-space operator learning for nonlinear model-order reduction of sharp-gradient systems, showing higher accuracy than POD-LaSDI at modest extra cost and introducing a point-cloud error metric.
Cellina uses supervised disentanglement to separate cell intrinsic states from spatial contexts for counterfactual predictions on tissue graphs, outperforming baselines on 2.5M+ cells from cancer and brain data.
EpiFormer improves epitope prediction F1 score by over 40% via early-fusion cross-attention in GNN layers and sparsity-aware objectives, while recovering known biology as emergent behavior.
Operator-level factorial benchmark of 84 MPNN configurations finds message-seed initialization and node-edge fusion drive performance on MoleculeNet tasks more than node updates.
SiST-GNN performs simultaneous spatial-temporal message passing on a temporally augmented graph and reports 109-277% gains in fixed-split dynamic link prediction over prior methods.
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
FROG makes full-resolution graph structure learnable in relational deep learning by modeling table roles as optimizable components in message passing, regularized by functional dependency constraints.
Contrastive Message Passing lets GNNs apply similarity-preserving transforms to positive edges and dissimilarity-inducing transforms to negative edges via soft positive semidefinite constraints on weights, yielding gains in low-label high-homophily regimes.
OgBench is the first benchmark platform for GNN graph-level prediction in the n << p omics regime and finds that common GNNs often underperform MLPs and classical baselines.
NeurPRISE trains a GNN-Transformer via imitation learning to mimic a lookahead heuristic for scenario reduction in 2RO, delivering 7-200x speedups with competitive regret on three test problems and zero-shot generalization.
Vibrational mode graphs from molecular dynamics enable sequence-free protein function prediction via graph neural networks, with entrainment improving signals for collective dynamics.
ATLAS achieves 12-30x faster out-of-core full-graph GNN inference on graphs up to 4B edges by switching to broadcast-based layer-wise execution with graph reordering, minimum-pending-message eviction, and GPU-accelerated tiered memory-disk hierarchy.
PiGGO integrates a learned graph neural ODE as the continuous-time dynamics model within an extended Kalman filter to enable online virtual sensing and uncertainty-aware state estimation for nonlinear dynamic systems with unknown model form and sparse sensing.
HopRank is a self-supervised LLM-tuning method that turns node classification into link prediction via hierarchical hop-based preference sampling, matching supervised GNN performance with zero labeled data on text-attributed graphs.
HND models hypergraph feature propagation as an anisotropic diffusion process governed by a continuous-time PDE, discretized into stable neural layers with energy dissipation and boundedness guarantees.
LOGGIA is a delay-aware graph neural routing algorithm using pre-training and RL that outperforms shortest-path and other neural methods in realistic network simulations.
NEAT achieves state-of-the-art 3D molecular generation on QM9 and GEOM-Drugs via a neighborhood-guided autoregressive set transformer that ensures atom-level permutation invariance and offers a significant speed advantage.
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
A systematic method leveraging Weisfeiler-Leman coloring to mine class-discriminating motifs as proxy explanations, enabling the creation of the OpenGraphXAI benchmark suite from real-world datasets.
Oblivious MPGNNs cannot simulate WL color refinement with shallow depth and small messages without randomness; bounded-error randomness enables logarithmic resources for large color sets, while small color sets force layer-message trade-offs.
HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduced parameter counts.
Graph Transformers are shown to be vulnerable to adaptive structure-perturbation attacks, which can also be used for effective adversarial training to improve robustness.
ElemeNet is a unified ML software package for molecular property prediction across elements 1-100 with built-in uncertainty quantification and competitive benchmarks on diverse chemistry datasets.
citing papers explorer
-
Spatial Support Matters: Geometry-Aware Graph Fusion for Rainfall Field Reconstruction
A geometry-aware multi-support heterogeneous GNN fuses point, line, and grid rainfall observations via cross-support message passing to reconstruct fields at arbitrary resolutions, reducing RMSE by 23.2% over baselines on Singapore data.
-
Efficient implementation of graph autoencoders for model-order reduction of systems with sharp gradients
GNN-LaSDI combines graph autoencoders with latent-space operator learning for nonlinear model-order reduction of sharp-gradient systems, showing higher accuracy than POD-LaSDI at modest extra cost and introducing a point-cloud error metric.
-
Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement
Cellina uses supervised disentanglement to separate cell intrinsic states from spatial contexts for counterfactual predictions on tissue graphs, outperforming baselines on 2.5M+ cells from cancer and brain data.
-
EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning
EpiFormer improves epitope prediction F1 score by over 40% via early-fusion cross-attention in GNN layers and sparsity-aware objectives, while recovering known biology as emergent behavior.
-
What drives performance in molecular MPNNs? An operator-level factorial benchmark
Operator-level factorial benchmark of 84 MPNN configurations finds message-seed initialization and node-edge fusion drive performance on MoleculeNet tasks more than node updates.
-
'Si'multaneous 'S'patial-'T'emporal Message Passing for Dynamic Graph Representation Learning
SiST-GNN performs simultaneous spatial-temporal message passing on a temporally augmented graph and reports 109-277% gains in fixed-split dynamic link prediction over prior methods.
-
Learning Dynamic Stability Landscapes in Synchronization Networks
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
-
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning
FROG makes full-resolution graph structure learnable in relational deep learning by modeling table roles as optimizable components in message passing, regularized by functional dependency constraints.
-
Learning over Positive and Negative Edges with Contrastive Message Passing
Contrastive Message Passing lets GNNs apply similarity-preserving transforms to positive edges and dissimilarity-inducing transforms to negative edges via soft positive semidefinite constraints on weights, yielding gains in low-label high-homophily regimes.
-
OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data
OgBench is the first benchmark platform for GNN graph-level prediction in the n << p omics regime and finds that common GNNs often underperform MLPs and classical baselines.
-
Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty
NeurPRISE trains a GNN-Transformer via imitation learning to mimic a lookahead heuristic for scenario reduction in 2RO, delivering 7-200x speedups with competitive regret on three test problems and zero-shot generalization.
-
Frequency-Space Mechanics: A Sequence and Coordinate-Free Representation for Protein Function Prediction
Vibrational mode graphs from molecular dynamics enable sequence-free protein function prediction via graph neural networks, with entrainment improving signals for collective dynamics.
-
ATLAS: Efficient Out-of-Core Inference for Billion-Scale Graph Neural Networks
ATLAS achieves 12-30x faster out-of-core full-graph GNN inference on graphs up to 4B edges by switching to broadcast-based layer-wise execution with graph reordering, minimum-pending-message eviction, and GPU-accelerated tiered memory-disk hierarchy.
-
PiGGO: Physics-Guided Learnable Graph Kalman Filters for Virtual Sensing of Nonlinear Dynamic Structures under Uncertainty
PiGGO integrates a learned graph neural ODE as the continuous-time dynamics model within an extended Kalman filter to enable online virtual sensing and uncertainty-aware state estimation for nonlinear dynamic systems with unknown model form and sparse sensing.
-
HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification
HopRank is a self-supervised LLM-tuning method that turns node classification into link prediction via hierarchical hop-based preference sampling, matching supervised GNN performance with zero labeled data on text-attributed graphs.
-
Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing
HND models hypergraph feature propagation as an anisotropic diffusion process governed by a continuous-time PDE, discretized into stable neural layers with energy dissipation and boundedness guarantees.
-
Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms
LOGGIA is a delay-aware graph neural routing algorithm using pre-training and RL that outperforms shortest-path and other neural methods in realistic network simulations.
-
NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
NEAT achieves state-of-the-art 3D molecular generation on QM9 and GEOM-Drugs via a neighborhood-guided autoregressive set transformer that ensures atom-level permutation invariance and offers a significant speed advantage.
-
Joint Relational Database Generation via Graph-Conditional Diffusion Models
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
-
A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring
A systematic method leveraging Weisfeiler-Leman coloring to mine class-discriminating motifs as proxy explanations, enabling the creation of the OpenGraphXAI benchmark suite from real-world datasets.
-
How Hard Is It for Message-Passing GNNs to Simulate One Weisfeiler-Lehman Color-Refinement Step?
Oblivious MPGNNs cannot simulate WL color refinement with shallow depth and small messages without randomness; bounded-error randomness enables logarithmic resources for large color sets, while small color sets force layer-message trade-offs.
-
Heterogeneous Sheaf Neural Networks
HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduced parameter counts.
-
Adversarial Robustness of Graph Transformers
Graph Transformers are shown to be vulnerable to adaptive structure-perturbation attacks, which can also be used for effective adversarial training to improve robustness.
-
ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table
ElemeNet is a unified ML software package for molecular property prediction across elements 1-100 with built-in uncertainty quantification and competitive benchmarks on diverse chemistry datasets.
-
Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems
SIES learns generalizable local coupling operators via signed source-target attention for controllable synchronization in graph dynamical systems and applies the principle to heterophilous graph representation learning.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and long-term agent benchmarks.
-
Invariant-Based Diagnostics for Graph Benchmarks
Graph invariants serve as expressive, task-agnostic baselines that characterize structural heterogeneity and match trained models across 26 datasets, indicating that expressivity is not the primary driver of performance.
-
Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning
Mochi aligns pre-training with inference via meta-learning for efficient graph foundation models, matching or exceeding prior models on 25 datasets with 8-27x less training time.
-
TACENR: Task-Agnostic Contrastive Explanations for Node Representations
TACENR introduces a contrastive-learning method that identifies the most influential attribute, proximity, and structural features in node representations in a task-agnostic manner.
-
LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval
LogosKG delivers a novel hardware-aligned system for efficient multi-hop retrieval on billion-edge knowledge graphs without sacrificing fidelity, demonstrated via biomedical KG-LLM applications.
-
A Structure-Preserving Graph Neural Solver for Parametric Hyperbolic Conservation Laws
A structure-preserving GNN solver for parametric hyperbolic conservation laws achieves superior long-horizon stability and orders-of-magnitude speedups over high-resolution simulations on supersonic flow benchmarks.
-
PUFFIN: Protein Unit Discovery with Functional Supervision
PUFFIN discovers protein units by jointly learning structural partitioning of residue graphs and functional supervision via a graph neural network with structure-aware pooling.
-
TOPCELL: Topology Optimization of Standard Cell via LLMs
TOPCELL reformulates standard cell topology optimization as an LLM generative task with GRPO fine-tuning, outperforming base models and matching exhaustive solvers with 85.91x speedup in 2nm/7nm industrial flows.
-
Disorder-induced chirality in superconductor-ferromagnet heterostructures revealed by neutron scattering and multiscale modeling
Chemical disorder plus compositional gradients in FePd films produce finite Dzyaloshinskii-Moriya interactions that stabilize chiral magnetic modulations with mixed Bloch-Néel character.
-
FlexMS is a flexible framework for benchmarking deep learning-based mass spectrum prediction tools in metabolomics
FlexMS is a new flexible benchmarking framework that lets researchers dynamically combine deep learning architectures and evaluate their mass spectrum prediction performance on public metabolomics datasets using multiple metrics and retrieval tasks.
-
SHIRO: Near-Optimal Communication Strategies for Distributed Sparse Matrix Multiplication
SHIRO achieves geometric mean speedups of 221.5x to 8.8x over four baselines in distributed SpMM on up to 128 GPUs by exploiting sparsity patterns and two-tier network topologies.
-
Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation
DART mitigates structural overfitting in graph missing-feature imputation via global structural augmentation, masked-autoencoder semantic rectification, and test-time distribution rectification, outperforming prior methods on transductive and inductive tasks including a new real-missing dataset.
-
Graph-Based Alternatives to LLMs for Human Simulation
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
-
Weisfeiler and Leman Follow the Arrow of Time: Expressive Power of Message Passing in Temporal Event Graphs
Introduces consistent event graph isomorphism and a temporal Weisfeiler-Leman algorithm to analyze and improve the expressive power of message passing in temporal event graphs.
-
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
DGL is a graph-centric library that optimizes GNNs via generalized sparse tensor operations, transparent graph-based optimizations, and framework-neutral design, claiming superior speed and memory use over other GNN frameworks.
-
Hierarchical Graph Learning for Calendar Spread Strategies in Commodity Futures Markets
A hierarchical graph neural network predicts commodity futures prices to generate calendar spread positions that outperform benchmarks on CME data by leveraging maturity-dependent correlations.
-
SEAGAN: domain-Specific and Edge-Aware Graph Attention Network for Dynamic Plant Processes
SEAGAN applies a domain-specific graph attention network to classify limitation states in A-Ci curves, achieving F1-score 0.857 and accuracy 0.882 on synthetic data with known ground truth.
-
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing
Message passing trivializes positive sample maximization in GCL via Dirichlet energy smoothing; SPGCL mitigates this by propagating only high-energy features and using low-energy ones for positive sampling.
-
Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism
LLMs succeed at graph isomorphism detection but fail to recognize isomorphic graphs under node label permutation, indicating pattern exploitation over topological understanding.
-
Physics-Informed Graph Neural Network Surrogates for Turbulent Nanoparticle Dispersion in Dental Clinical Environments
ELGIN is a graph-based physics-informed surrogate model that predicts carrier flow and polydisperse particle motion in dental aerosol scenarios, achieving lower tracking errors and 37x speedup versus full OpenFOAM CFD in a preliminary single-case test.
-
A complete discussion on fully reconfigurable, digital, scalable, graph and sparsity-aware near-memory accelerator for graph neural networks
NEM-GNN proposes a scalable DAC/ADC-less PIM architecture for GNNs with early termination and CAR execution, claiming 80-230x performance and 850-1134x energy gains over prior accelerators.
-
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
-
Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks
A BART-GraphSAGE hybrid achieves ROC-AUC 67.40 on one RelBench task, competitive with LightGBM but still behind specialized relational deep learning and foundation models.
-
Astro Generative Network: A Variational Framework for Controlled Node Insertion in Incomplete Complex Networks
AGN is a variational framework for inserting plausible new nodes into incomplete networks by latent sampling and similarity attachment, shown on synthetic data to keep clustering and modularity changes modest compared to a baseline that allows new-new edges.