Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs

By Minjie Wang, Lingfan Yu, Da Zheng, Quan Gan, Yujie Gai, Zihao Ye, Mufei Li, Jinjing Zhou, Qi Huang, Chao Ma and 8 more. arXiv.org, 2019

884 citations recorded by the source corpus.

Accelerating research in the emerging field of deep graph learning requires new tools. Such systems should support graph as the core abstraction and take care to maintain both forward (i.e. supporting new research ideas) and backward (i.e. integration with existing components) compatibility. In this paper, we present Deep Graph Library (DGL). DGL enables arbitrary message handling and mutation operators, flexible propagation rules, and is framework agnostic so as to leverage high-performance tensor, autograd operations, and other feature extraction modules already available in existing frameworks. DGL carefully handles the sparse and irregular graph structure, deals with graphs big and small which may change dynamically, fuses operations, and performs auto-batching, all to take advantages of modern hardware. DGL has been tested on a variety of models, including but not limited to the popular Graph Neural Networks (GNN) and its variants, with promising speed, memory footprint and scalability.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/fd075bcdf2d7e13d23f7c249a8eded343d5bbe3b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Hardware and Architecture

Citations in the corpus

Benchmarking Graph Neural Networks (2023, methodology): “[85] Minjie Wang, Lingfan Yu, Da Zheng, Quan Gan, Yu Gai, Zihao Ye, Mufei Li, Jinjing Zhou, Qi Huang, Chao Ma, Ziyue Huang, Qipeng Guo, Hao Zhang, Haibin Lin, Junbo Zhao, Jinyang Li, Alexander J Smola, and Zheng Zhang.”
Open Graph Benchmark: Datasets for Machine Learning on Graphs (2020, methodology): “Speciﬁcally, (Wang et al., 2019b), which does not reﬂect the practical usage.”
DropEdge: Towards Deep Graph Convolutional Networks on Node Classification (2019, methodology): “For GraphSAGE, we utilize the Pytorch version implemented by DGL(Wang et al., 2019).”
Probabilistic Dual Network Architecture Search on Graphs (2020, methodology): “For the Cora dataset, to ensure a consistent comparison to GraphNAS (Gao et al., 2019), we used the data splits provided by the Deep Graph Library (Wang et al., 2019).”
TUDataset: A collection of benchmark datasets for learning with graphs (2020, methodology): “All datasets are provided in a standard dataset format at www.graphlearning.io and are easily accessible from popular graph learning frameworks such as P YTORCH G EOMETRIC (Fey & Lenssen, 2019) 1 and DGL (Wang et al., 2019) 2 .”
Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models (2020, methodology): “Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit‑learn: machine learning in Python.”
A Gentle Introduction to Deep Learning for Graphs (2019, methodology): “Deep Graph Library: Towards efficient and scalable deep learning on graphs.”
A Comprehensive Survey on Graph Neural Networks (2019, background): “Most recently, the Deep Graph Library (DGL) 5 [133] is released which provides a fast implementation of many GNNs on top of popular deep learning platforms such as PyTorch and MXNet.”
T RANSFORMER -XH: M ULTI - HOP Q UESTION A N - SWERING WITH E X TRA H OP A TTENTION (2019, methodology): “We use DGL (Wang et al., 2019) for implementing Transformer-XH and CogQA (w. BERT IR) with batch size 1 (i.e., one graph for each batch), and keep the other parameters same as default BERT setting.”
TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery (2022, methodology): “DGL additionally supports MXNet (Chen et al., 2015) backend.”
A Generalization of Transformer Networks to Graphs (2020, methodology): “For experiments, we follow the benchmarking protocol introduced in Dwivedi et al. (2020) based on PyTorch (Paszke et al. 2019) and DGL (Wang et al. 2019).”
Machine Learning on Graphs: A Model and Comprehensive Taxonomy (2020, neutral): “, 2020) and graph embedding libraries (Fey and Lenssen, 2019; Wang et al., 2019; Goyal and Ferrara, 2018a).”
Deep Learning on Graphs: A Survey (2018, neutral): “com/rusty1s/pytorch geometric PyTorch Improved efficiency, unified operations, comprehensive existing methods Deep Graph Library [165] https://github.”
Graph Neural Networks with Learnable Structural and Positional Representations (2021, methodology): “VPD would like to thank Andreea Deac for her helpful feedback, Quan Gan for his support on the DGL library, Gabriele Corso for answering questions related to the PNA model, and Chaitanya K. Joshi for useful comments.”
From Canonical Correlation Analysis to Self-supervised Graph Neural Networks (2021, methodology): “[49] Minjie Wang, Lingfan Yu, Da Zheng, Quan Gan, Yu Gai, Zihao Ye, Mufei Li, Jinjing Zhou, Qi Huang, Chao Ma, Ziyue Huang, Qipeng Guo, Hao Zhang, Haibin Lin, Junbo Zhao, Jinyang Li, Alexander J.”