A Unified Lottery Ticket Hypothesis for Graph Neural Networks

Authors: Tianlong Chen, Yongduo Sui, Xuxi Chen, Aston Zhang, Zhangyang Wang

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our proposal has been experimentally verified across various GNN architectures and diverse tasks, on both small-scale graph datasets (Cora, Citeseer and Pub Med), and large-scale datasets from the challenging Open Graph Benchmark (OGB).
Researcher Affiliation Collaboration 1Department of Electrical and Computer Engineering, University of Texas at Austin 2University of Science and Technology of China 3AWS Deep Learning.
Pseudocode Yes Algorithm 1 Unified GNN Sparsification (UGS)
Open Source Code Yes Codes are at https://github. com/VITA-Group/Unified-LTH-GNN.
Open Datasets Yes Datasets We use popular semi-supervised graph datasets: Cora, Citeseer and Pub Med (Kipf & Welling, 2016), for both node classification and link prediction tasks. For experiments on large-scale graphs, we use the Open Graph Benchmark (OGB) (Hu et al., 2020), such as Ogbn-Ar Xiv, Ogbn Proteins, and Ogbl-Collab.
Dataset Splits Yes Other details such as the datasets trainval-test splits are included in Appendix A1.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions 'NetworkX' but does not provide specific version numbers for software dependencies or frameworks used for the experiments.
Experiment Setup Yes More detailed configurations such as learning rate, training iterations, and hyperparameters in UGS, are referred to Appendix A1.