37 citations · 169 across the 20 of their papers we have counts for
9 papers · 1 filter
On the Initialization of Graph Neural Networks
Jiahang Li, Yakun Song, Xiang Song +1
Graph Neural Networks (GNNs) have displayed considerable promise in graph representation learning across various applications. The core learning process requires the initialization…
TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning
Jing Zhu, Xiang Song, Vassilis N. Ioannidis +2
How can we enhance the node features acquired from Pretrained Models (PMs) to better suit downstream graph learning tasks? Graph Neural Networks (GNNs) have become the state-of-the…
DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training
Hongkuan Zhou, Da Zheng, Xiang Song +2
Memory-based Temporal Graph Neural Networks are powerful tools in dynamic graph representation learning and have demonstrated superior performance in many real-world applications.…
Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
Han Xie, Da Zheng, Jun Ma +9
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be…
Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices
Jing Zhu, Yuhang Zhou, Vassilis N. Ioannidis +4
While Graph Neural Networks (GNNs) are remarkably successful in a variety of high-impact applications, we demonstrate that, in link prediction, the common practices of including th…
IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research
Arpandeep Khatua, Vikram Sharma Mailthody, Bhagyashree Taleka +3
Graph neural networks (GNNs) have shown high potential for a variety of real-world, challenging applications, but one of the major obstacles in GNN research is the lack of large-sc…
PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction
Shichang Zhang, Jiani Zhang, Xiang Song +4
Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and he…
FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
Kezhao Huang, Haitian Jiang, Minjie Wang +7
A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU. Due to limited GPU memory, expensive d…
Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures
Kun Wu, Mert Hidayetoğlu, Xiang Song +4
Relational graph neural networks (RGNNs) are graph neural networks with dedicated structures for modeling the different types of nodes and edges in heterogeneous graphs. While RGNN…