Distributed graph neural network training: A survey

Y Shao, H Li, X Gu, H Yin, Y Li, X Miao… - ACM Computing …, 2024 - dl.acm.org
Graph neural networks (GNNs) are a type of deep learning models that are trained on
graphs and have been successfully applied in various domains. Despite the effectiveness of …

LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings

N Liao, S Luo, X Li, J Shi - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Abstract Heterophilous Graph Neural Network (GNN) is a family of GNNs that specializes in
learning graphs under heterophily, where connected nodes tend to have different labels …

Scalable and efficient full-graph gnn training for large graphs

X Wan, K Xu, X Liao, Y Jin, K Chen, X Jin - Proceedings of the ACM on …, 2023 - dl.acm.org
Graph Neural Networks (GNNs) have emerged as powerful tools to capture structural
information from graph-structured data, achieving state-of-the-art performance on …

Adaptive message quantization and parallelization for distributed full-graph gnn training

B Wan, J Zhao, C Wu - Proceedings of Machine Learning …, 2023 - proceedings.mlsys.org
Distributed full-graph training of Graph Neural Networks (GNNs) over large graphs is
bandwidth-demanding and time-consuming. Frequent exchanges of node features …

DUCATI: A dual-cache training system for graph neural networks on giant graphs with the GPU

X Zhang, Y Shen, Y Shao, L Chen - … of the ACM on Management of Data, 2023 - dl.acm.org
Recently Graph Neural Networks (GNNs) have achieved great success in many
applications. The mini-batch training has become the de-facto way to train GNNs on giant …

A survey on graph neural network acceleration: Algorithms, systems, and customized hardware

S Zhang, A Sohrabizadeh, C Wan, Z Huang… - arXiv preprint arXiv …, 2023 - arxiv.org
Graph neural networks (GNNs) are emerging for machine learning research on graph-
structured data. GNNs achieve state-of-the-art performance on many tasks, but they face …

Redundancy-free high-performance dynamic GNN training with hierarchical pipeline parallelism

Y Xia, Z Zhang, H Wang, D Yang, X Zhou… - Proceedings of the 32nd …, 2023 - dl.acm.org
Temporal Graph Neural Networks (TGNNs) extend the success of Graph Neural Networks to
dynamic graphs. Distributed TGNN training requires efficiently tackling temporal …

Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective

H Yuan, Y Liu, Y Zhang, X Ai, Q Wang, C Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
Many Graph Neural Network (GNN) training systems have emerged recently to support
efficient GNN training. Since GNNs embody complex data dependencies between training …

Surel+: Moving from walks to sets for scalable subgraph-based graph representation learning

H Yin, M Zhang, J Wang, P Li - arXiv preprint arXiv:2303.03379, 2023 - arxiv.org
Subgraph-based graph representation learning (SGRL) has recently emerged as a powerful
tool in many prediction tasks on graphs due to its advantages in model expressiveness and …

ETC: Efficient Training of Temporal Graph Neural Networks over Large-scale Dynamic Graphs

S Gao, Y Li, Y Shen, Y Shao, L Chen - Proceedings of the VLDB …, 2024 - dl.acm.org
Dynamic graphs play a crucial role in various real-world applications, such as link prediction
and node classification on social media and e-commerce platforms. Temporal Graph Neural …