Graph WaveNet for Deep Spatial-Temporal Graph Modeling

Authors: Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.
Researcher Affiliation Academia 1Centre for Artificial Intelligence, FEIT, University of Technology Sydney, Australia 2Faculty of Information Technology, Monash University, Australia zonghan.wu-3@student.uts.edu.au, shirui.pan@monash.edu, {guodong.long, jing.jiang, chengqi.zhang}@uts.edu.au
Pseudocode No The paper does not include a dedicated pseudocode block or algorithm listing.
Open Source Code Yes The source codes of Graph Wave Net are publicly available from https://github.com/ nnzhan/Graph-Wave Net.
Open Datasets Yes We verify Graph Wave Net on two public traffic network datasets, METR-LA and PEMS-BAY released by Li et al. [2018b].
Dataset Splits Yes The datasets are split in chronological order with 70% for training, 10% for validation and 20% for testing.
Hardware Specification Yes Our experiments are conducted under a computer environment with one Intel(R) Core(TM) i9-7900X CPU @ 3.30GHz and one NVIDIA Titan Xp GPU card.
Software Dependencies No The paper does not provide specific version numbers for software dependencies such as programming languages, libraries, or frameworks (e.g., Python version, PyTorch/TensorFlow version).
Experiment Setup Yes To cover the input sequence length, we use eight layers of Graph Wave Net with a sequence of dilation factors 1, 2, 1, 2, 1, 2, 1, 2. We use Equation 4 as our graph convolution layer with a diffusion step K = 2. We randomly initialize node embeddings by a uniform distribution with a size of 10. We train our model using Adam optimizer with an initial learning rate of 0.001. Dropout with p=0.3 is applied to the outputs of the graph convolution layer.