graphs-6

Graph Sampling

3260 papers • 126 benchmarks • 313 datasets

Training GNNs or generating graph embeddings requires graph samples.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in graph-sampling-6

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find graph-sampling-6 models and implementations

benedekrozemberczki/littleballoffur

4 papers 658

Datasets

Friendster

LastFM Asia

Subtasks

No subtasks available.

Most implemented papers

GraphSAINT: Graph Sampling Based Inductive Learning Method

Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, R. Kannan, V. Prasanna•Tue Jul 09 2019

GraphSAINT is proposed, a graph sampling based inductive learning method that improves training efficiency in a fundamentally different way and can decouple the sampling process from the forward and backward propagation of training, and extend GraphSAINT with other graph samplers and GCN variants.

1104

Content

GraphSAINT/GraphSAINT

2 papers 431

0

Paper Graph

Heterogeneous Graph Transformer

Yuxiao Dong, Ziniu Hu, Kuansan Wang, Yizhou Sun•Mon Mar 02 2020

The proposed HGT model consistently outperforms all the state-of-the-art GNN baselines by 9–21 on various downstream tasks, and the heterogeneous mini-batch graph sampling algorithm—HGSampling—for efficient and scalable training.

1455 0

Paper Graph

SIGN: Scalable Inception Graph Neural Networks

M. Bronstein, Emanuele Rossi, B. Chamberlain, Fabrizio Frasca, D. Eynard, Federico Monti•Wed Apr 22 2020

This paper proposes a new, efficient and scalable graph deep learning architecture which sidesteps the need for graph sampling by using graph convolutional filters of different size that are amenable to efficient precomputation, allowing extremely fast training and inference.

444 0

Paper Graph

Training Graph Neural Networks with 1000 Layers

V. Koltun, Matthias Müller, Bernard Ghanem, Guohao Li•Sun Jun 13 2021

This work finds that reversible connections in combination with deep network architectures enable the training of overparameterized GNNs that significantly outperform existing methods on multiple datasets.

282 0

Paper Graph

Accurate, Efficient and Scalable Graph Embedding

Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, R. Kannan, V. Prasanna•Sat Oct 27 2018

This paper proposes novel parallelization techniques for graph sampling-based GCNs that achieve superior scalable performance on very large graphs without compromising accuracy, and demonstrates that the parallel graph embedding outperforms state-of theart methods in scalability, efficiency and accuracy on several large datasets.

81 0

Paper Graph

Accurate, Efficient and Scalable Training of Graph Neural Networks

Hongkuan Zhou, Ajitesh Srivastava, R. Kannan, V. Prasanna, Hanqing Zeng•Sun Oct 04 2020

The proposed training outperforms the state-of-the-art in scalability, efficiency and accuracy simultaneously simultaneously and enables fast training of deeper GNNs, as demonstrated by orders of magnitude speedup compared to the Tensorflow implementation.

10 0

Paper Graph

Sampling from large graphs

J. Leskovec, C. Faloutsos•Sat Aug 19 2006

The best performing methods are the ones based on random-walks and "forest fire"; they match very accurately both static as well as evolutionary graph patterns, with sample sizes down to about 15% of the original graph.

1351 0

Paper Graph

Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data

Victor Veitch, D. Blei, Morgane Austern, Wenda Zhou, Peter Orbanz•Tue Jun 26 2018

This work defines an empirical risk for relational data and obtains stochastic gradients for this empirical risk that are automatically unbiased by integrating fast implementations of graph sampling schemes with standard automatic differentiation tools, providing an efficient turnkey solver for the risk minimization problem.

11 0

Paper Graph

Influence Maximization in Unknown Social Networks: Learning Policies for Effective Graph Sampling

Bryan Wilder, Balaraman Ravindran, Milind Tambe, Harshavardhan Kamarthi, Priyesh Vijayan•Sun Jul 07 2019

This work proposes a reinforcement learning framework to discover effective network sampling heuristics by leveraging automatically learnt node and graph representations that encode important structural properties of the network.

45 0

Paper Graph

Neighborhood Matching Network for Entity Alignment

Yansong Feng, Xiao Liu, Dongyan Zhao, Yuting Wu•Mon May 11 2020

Neighborhood Matching Network (NMN), a novel entity alignment framework for tackling the structural heterogeneity challenge, can well estimate the neighborhood similarity in more tough cases and significantly outperforms 12 previous state-of-the-art methods.

140 0

Paper Graph

Adding a benchmark result helps the community track progress.