1.9k citations · 2.9k across the 29 of their papers we have counts for
14 papers · 1 filter
Griffin: Towards a Graph-Centric Relational Database Foundation Model
Yanbo Wang, Xiyuan Wang, Quan Gan +4
We introduce Griffin, the first foundation model attemptation designed specifically for Relational Databases (RDBs). Unlike previous smaller models focused on single RDB tasks, Gri…
DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs
Jiahui Liu, Zhenkun Cai, Zhiyong Chen +1
Attention Graph Neural Networks (AT-GNNs), such as GAT and Graph Transformer, have demonstrated superior performance compared to other GNNs. However, existing GNN systems struggle…
DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training
Renjie Liu, Yichuan Wang, Xiao Yan +5
Graph neural networks (GNNs) are machine learning models specialized for graph data and widely used in many applications. To train GNNs on large graphs that exceed CPU memory, seve…
4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs
Minjie Wang, Quan Gan, David Wipf +17
Although RDBs store vast amounts of rich, informative data spread across interconnected tables, the progress of predictive machine learning models as applied to such tasks arguably…
BloomGML: Graph Machine Learning through the Lens of Bilevel Optimization
Amber Yijia Zheng, Tong He, Yixuan Qiu +2
Bilevel optimization refers to scenarios whereby the optimal solution of a lower-level energy function serves as input features to an upper-level objective of interest. These optim…
MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy
Haitian Jiang, Renjie Liu, Zengfeng Huang +5
Among the many variants of graph neural network (GNN) architectures capable of modeling data with cross-instance relations, an important subclass involves layers designed such that…
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…
DGI: Easy and Efficient Inference for GNNs
Peiqi Yin, Xiao Yan, Jinjing Zhou +5
While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopte…
BiFeat: Supercharge GNN Training via Graph Feature Quantization
Yuxin Ma, Ping Gong, Jun Yi +4
Graph Neural Networks (GNNs) is a promising approach for applications with nonEuclidean data. However, training GNNs on large scale graphs with hundreds of millions nodes is both r…
CEP3: Community Event Prediction with Neural Point Process on Graph
Xuhong Wang, Sirui Chen, Yixuan He +4
Many real world applications can be formulated as event forecasting on Continuous Time Dynamic Graphs (CTDGs) where the occurrence of a timed event between two entities is represen…
DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs
Da Zheng, Chao Ma, Minjie Wang +6
Graph neural networks (GNN) have shown great success in learning from graph-structured data. They are widely used in various applications, such as recommendation, fraud detection,…
FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems
Yuwei Hu, Zihao Ye, Minjie Wang +6
Graph neural networks (GNNs) are gaining increasing popularity as a promising approach to machine learning on graphs. Unlike traditional graph workloads where each vertex/edge is a…
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
Minjie Wang, Da Zheng, Zihao Ye +12
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 im…
Learned Indexes for Dynamic Workloads
Chuzhe Tang, Zhiyuan Dong, Minjie Wang +2
The recent proposal of learned index structures opens up a new perspective on how traditional range indexes can be optimized. However, the current learned indexes assume the data d…