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..
MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification
Authors: Xinya Qin, Lu Bai, Lixin Cui, Ming Li, Hangyuan Du, Edwin R. Hancock
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the proposed Multi Net model on several benchmark graph classification datasets, including MUTAG, PTC_MR, ENZYMES, PROTEINS, DD, IMDB-B, and IMDB-M. The classification accuracy and standard error are reported in Table 1, and the last column represents the average rank. ... We conduct ablation studies by removing individual modules to evaluate the contribution of each component in the proposed Multi Net. |
| Researcher Affiliation | Academia | 1School of Artificial Intelligence, Beijing Normal University, Beijing, China. 2School of Information, Central University of Finance and Economics, Beijing, China. 3Zhejiang Institute of Optoelectronics, Jinhua, China. 4Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University, Jinhua, China. 5School of Computer and Information Technology, Shanxi University, Taiyuan, China. 6Department of Computer Science, University of York, York, United Kingdom. Xinya EMAIL, EMAIL |
| Pseudocode | No | The paper describes the model architecture and procedures using mathematical equations and textual descriptions in Section 3, but does not include a distinct pseudocode or algorithm block. |
| Open Source Code | Yes | Code is available at https://github.com/Xiaoqin0421/Multi Net |
| Open Datasets | Yes | We evaluate the proposed Multi Net model on several benchmark graph classification datasets, including MUTAG, PTC_MR, ENZYMES, PROTEINS, DD, IMDB-B, and IMDB-M. |
| Dataset Splits | Yes | To ensure statistical robustness, we perform ten runs of 10-fold cross-validation and report the mean classification accuracy along with the standard deviation 2. |
| Hardware Specification | Yes | All experiments are implemented in Py Torch and Py Torch Geometric, and executed on an NVIDIA Ge Force RTX 3090 GPU (24GB VRAM). |
| Software Dependencies | No | All experiments are implemented in Py Torch and Py Torch Geometric, and executed on an NVIDIA Ge Force RTX 3090 GPU (24GB VRAM). |
| Experiment Setup | Yes | For all datasets, we use a local subgraph convolution module with 3 to 4 layers, set the number of views to 8, the node embedding dimension to 32, and the number of aligned nodes during readout to 8, with Re LU as the activation function. The model is trained using the Adam optimizer, with hyperparameters such as learning rate and number of epochs tuned via validation. |