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

By Minjie Wang, Da Zheng, Zihao Ye, Quan Gan, Mufei Li, Xiang Song, Jinjing Zhou, Chao Ma, Lingfan Yu, Yujie Gai and 5 more. 2019

1,357 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/381411d740562de1e766dc8cc833844eb99dde01

How researchers see this paper

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

1. Xiangnan He
2. Yoshua Bengio
3. Chen Gao
4. Guohao Li
5. Shirui Pan
6. Yixin Liu
7. Uri Alon
8. Petar Velickovic

Citations in the corpus

• Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection (2021, methodology): “GCN, GraphSAGE and GAT are implemented based on DGL[41].”
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning (2021, methodology): “For RWR subgraph sampling, we use the existing graph sampling function from library DGL 0.3.1 [70].”
• How Attentive are Graph Attention Networks? (2021, methodology): “While GAT is one of the most popular GNN architectures (Bronstein et al., 2021) and is considered as the state-of-the-art neural architecture for learning with graphs (Wang et al., 2019a), we show that GATs do not actually compute dynamic attention, a fact that severely hinders their expressiveness.”
• Training Graph Neural Networks with 1000 Layers (2021, methodology): “We use Pytorch Geometric 1.6.1 (Fey & Lenssen, 2019) for all experiments except for the experiments with GATs where we use DGL 0.5.3 (Wang et al., 2019).”
• Rethinking Graph Neural Networks for Anomaly Detection (2022, methodology): “That is, (1) applying attention mechanisms to correlate different neighbors through various views (Wang et al., 2019a; Cui et al., 2020; Liu et al., 2021a), (2) using the resampling strategy to aggregate neighborhood information selectively (Dou et al., 2020; Liu et al., 2020; 2021b), (3) designing…”
• Rethinking Graph Transformers with Spectral Attention (2021, methodology): “The model is implemented in PyTorch [31] and DGL [38] and tested on established benchmarks from [15] and [21] provided under MIT license.”
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, methodology): “In addition, a few open-source tools have been released that can accelerate the research and development of GNN-based recommendation, such as PyG [48], DGL [174], and AliGraph [252].”
• Combinatorial optimization and reasoning with graph neural networks (2021, background): “However, promising ways to tackle the issue of gradient estimation have already emerged19 in the literature (Knöbelreiter et al., 2017; Wang et al., 2019; Vlastelica et al., 2020; Mandi and Guns, 2020; Niepert et al., 2021).”
• A critical look at the evaluation of GNNs under heterophily: are we really making progress? (2023, methodology): “Our baselines are implemented using PyTorch (Paszke et al., 2019) and DGL (Wang et al., 2019).”