Kernel Readout for Graph Neural Networks

Authors: Jiajun Yu, Zhihao Wu, Jinyu Cai, Adele Lu Jia, Jicong Fan

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental the experiments on eight benchmark datasets show that the proposed readout outperforms classical pooling methods such as Sum and seven state-of-the-art pooling methods such as SRead and Janossy GRU.
Researcher Affiliation Academia 1College of Information and Electrical Engineering, China Agricultural University, Beijing, China 2School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China 3Shenzhen Research Institute of Big Data, Shenzhen, China 4Institute of Data Science, National University of Singapore, Singapore 5College of Computer Science and Technology, Zhejiang University, Hangzhou, China
Pseudocode No The paper describes its method using text and equations (e.g., in Section 3.2 Detailed Method) but does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code Yes Code and Appendix are both available at https://github.com/jiajun CAU/Ker Read.
Open Datasets Yes This study employs a total of 8 graph-level datasets, comprising 6 chemical molecule datasets (MUTAG, DD, PROTEINS, NCI1, Mutagenicity and OGBG-Molhiv) and 2 social network graph datasets (IMDB-B, IMDB-M), these datasets are collected in TU datasets2 and open graph benchmark3.
Dataset Splits Yes Table 5: Mean accuracy (10 folds) and standard deviation on the 7 graph classification datasets with 5 kernel functions, where GCN is employed as the backbone.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types, memory) used for running its experiments.
Software Dependencies No The paper mentions employing 'officially released source code' and adopting parameters from 'respective papers' but does not specify any software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes Parameter Settings We employ the officially released source code and adopt the parameters suggested in the respective papers for all baseline readout functions and GNN backbones. Additional information on experimental settings can be found in Appendix C.