Towards Scalable and Deep Graph Neural Networks via Noise Masking
Authors: Yuxuan Liang, Wentao Zhang, Zeang Sheng, Ling Yang, Quanqing Xu, Jiawei Jiang, Yunhai Tong, Bin Cui
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on six real-world datasets demonstrate that model-simplification works equipped with RMask yield superior performance compared to their original version and can make a good trade-off between accuracy and efficiency. |
| Researcher Affiliation | Collaboration | Yuxuan Liang1, Wentao Zhang2*, Zeang Sheng3, Ling Yang3, Quanqing Xu4, Jiawei Jiang5, Yunhai Tong1, Bin Cui 3,6* 1School of Intelligence Science and Technology, Peking University 2Center for Machine Learning Research, Peking University 3School of CS & Key Laboratory of High Confidence Software Technologies (MOE), Peking University 4Ocean Base, Ant Group 5School of Computer Science, Wuhan University 6Institute of Computational Social Science, Peking University (Qingdao) EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1 outlines the overall process of RMask |
| Open Source Code | Yes | Our codes are available at https://github.com/Goo Liang/RMask. |
| Open Datasets | Yes | We evaluate the effectiveness of RMask on three widely used datasets (Cora, Citeseer, Pubmed) (Kipf and Welling 2017) and three large-scale datasets (ogbn-arxiv, ogbn-products, ogbn-papers100M) (Hu et al. 2020). |
| Dataset Splits | No | The details about all experiment settings and the network configurations are reported in the Appendix. |
| Hardware Specification | No | No specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments are provided in the main text. |
| Software Dependencies | No | No specific ancillary software details (e.g., library or solver names with version numbers) are provided in the main text. |
| Experiment Setup | No | The details about all experiment settings and the network configurations are reported in the Appendix. |