Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Node-wise Localization of Graph Neural Networks
Authors: Zemin Liu, Yuan Fang, Chenghao Liu, Steven C.H. Hoi
IJCAI 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we conduct extensive experiments on four benchmark graphs, and consistently obtain promising performance surpassing the state-of-theart GNNs. |
| Researcher Affiliation | Collaboration | Zemin Liu1 , Yuan Fang1 , Chenghao Liu2 and Steven C.H. Hoi1,2 1Singapore Management University, Singapore 2Salesforce Research Asia, Singapore |
| Pseudocode | No | The paper describes the proposed approach using mathematical formulations and descriptive text (e.g., equations 1-11) but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions 'Additional implementation details and experimental settings are included in Sections A and B of the supplemental material' and 'Details of the calculation are included in Section C of the supplemental material' but does not explicitly state that source code for the methodology is released or provide a link. |
| Open Datasets | Yes | Datasets. We utilize four benchmark datasets. They include two academic citation networks, namely Cora and Citeseer [Yang et al., 2016]... A similar citation network for Wikipedia articles called Chameleon [Pei et al., 2020] is also used. Finally, we use an e-commerce co-purchasing network called Amazon [Hou et al., 2020]. |
| Dataset Splits | Yes | For all datasets, we follow the standard split in the literature [Yang et al., 2016; Kipf and Welling, 2017; Veliˇckovi c et al., 2018], which uses 20 labeled nodes per class for training, 500 nodes for validation and 1000 nodes for testing. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU models, CPU types, or cloud instance specifications used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers, such as programming language versions, library versions (e.g., PyTorch, TensorFlow), or solver versions. |
| Experiment Setup | Yes | The dimension of the hidden layer defaults to 8, while we also present results using larger dimensions. The regularization of GNN parameters is set to λG = 0.0005. These settings are chosen via empirical validation, and are largely consistent with the literature [Perozzi et al., 2014; Kipf and Welling, 2017; Veliˇckovi c et al., 2018]. For our models, the additional regularizations are set to λL = λ = 1 (except for λ = 0.1 in LGAT). |