Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

2019/09/03 by Minjie Wang, Da Zheng, Wang, Minjie +27 · 35 citations
Computer Science · Mathematics · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Graph Theory and Algorithms #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Parallel Computing and Optimization Techniques #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1909.01315

Major update with significantly more results

openalex publication_date 2019/09/03 · arxiv created 2020/08/25 · arxiv updated 2020/08/26 · openalex created_date 2020/09/01 · openalex updated_date 2026/07/28

Abstract

Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and implementation of Deep Graph Library (DGL). DGL distills the computational patterns of GNNs into a few generalized sparse tensor operations suitable for extensive parallelization. By advocating graph as the central programming abstraction, DGL can perform optimizations transparently. By cautiously adopting a framework-neutral design, DGL allows users to easily port and leverage the existing components across multiple deep learning frameworks. Our evaluation shows that DGL significantly outperforms other popular GNN-oriented frameworks in both speed and memory consumption over a variety of benchmarks and has little overhead for small scale workloads.

Citations

• Spectral Networks and Locally Connected Networks on Graphs
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Neural Message Passing for Quantum Chemistry
• Graph Convolutional Matrix Completion
• Inductive Representation Learning on Large Graphs
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• Learning Deep Generative Models of Graphs
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
• Embedding Logical Queries on Knowledge Graphs
• How Powerful are Graph Neural Networks?
• Towards Efficient Large-Scale Graph Neural Network Computing
• Supervised Community Detection with Line Graph Neural Networks
• Simplifying Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• A Comprehensive Survey on Graph Neural Networks

Cited by

• Empowering GNNs for Domain Adaptation via Denoising Target Graph
• GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering
• Oral Tradition-Encoded NanyinHGNN: Integrating Nanyin Music Preservation and Generation through a Pipa-Centric Dataset
• LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences
• OptimES: Optimizing Federated Learning Using Remote Embeddings for Graph Neural Networks
• Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE
• TLV-HGNN: Thinking Like a Vertex for Memory-efficient HGNN Inference
• Structure-Informed Learning of Flat Band 2D Materials
• Geometric Learning in Black-Box Optimization: A GNN Framework for Algorithm Performance Prediction
• Optimizing Federated Learning using Remote Embeddings for Graph Neural Networks
• Interpreting and Unifying Graph Neural Networks with An Optimization Framework
• PIL-Net: a physics-informed graph convolutional network for predicting atomic multipoles
• Learnable Kernel Density Estimation for Graphs
• Local Augmentation for Graph Neural Networks
• Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features
• Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning
• PanRep: Graph neural networks for extracting universal node embeddings in heterogeneous graphs
• DIG: A Turnkey Library for Diving into Graph Deep Learning Research
• Neurospectrum: A Geometric and Topological Deep Learning Framework for Uncovering Spatiotemporal Signatures in Neural Activity
• Bag of Tricks for Node Classification with Graph Neural Networks
• Learning Large-Time-Step Molecular Dynamics with Graph Neural Networks
• Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining
• Learning Hierarchical Graph Neural Networks for Image Clustering
• Document Structure aware Relational Graph Convolutional Networks for Ontology Population
• CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design
• Graph Inference Representation: Learning Graph Positional Embeddings with Anchor Path Encoding
• Network In Graph Neural Network
• Graph Neural Planning and Predictive Control for Multi-Robot Communication-Constrained Unlabeled Motion Planning
• Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data
• Accurate Prediction of Free Solvation Energy of Organic Molecules via Graph Attention Network and Message Passing Neural Network from Pairwise Atomistic Interactions
• p2pGNN: A Decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks
• Divergent Paths: Separating Homophilic and Heterophilic Learning for Enhanced Graph-level Representations
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Scalable Graph Neural Networks for Heterogeneous Graphs
• HP-GNN: Generating High Throughput GNN Training Implementation on CPU-FPGA Heterogeneous Platform
• Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs

Related

• Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains
• Efficient Graph Deep Learning in TensorFlow with tf_geometric
• GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research
• oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation
• CogDL: A Comprehensive Library for Graph Deep Learning