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 [1].
Rethinking Causal Relationships Learning in Graph Neural Networks
Authors: Hang Gao, Chengyu Yao, Jiangmeng Li, Lingyu Si, Yifan Jin, Fengge Wu, Changwen Zheng, Huaping Liu
AAAI 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Through a series of experiments conducted on both synthetic datasets and other real-world datasets, we empirically validate the effectiveness of the proposed module. Our multiple experiments on both artificially synthesized datasets and real-world datasets have demonstrated the efficacy of R-CAM. Results are summarized in Table 6. |
| Researcher Affiliation | Academia | Hang Gao 1, 2*, Chengyu Yao1, 2*, Jiangmeng Li 1, 3, Lingyu Si 1, 2, Yifan Jin 1, 2, Fengge Wu 1, 2 , Changwen Zheng 1, 2, Huaping Liu 4 1Science and Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences 2University of Chinese Academy of Sciences 3State Key Laboratory of Intelligent Game 4Department of Computer Science and Technology, Tsinghua University EMAIL, EMAIL |
| Pseudocode | No | The paper describes the proposed module and its operations in text and mathematical formulas but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | The codes are available at https: //github.com/yaoyao-yaoyao-cell/CRCG. |
| Open Datasets | Yes | To order to comprehensively analyze various GNN models from a causal learning perspective, we constructed an artificially synthesized dataset with known and controllable causal relationships between data and labels. The codes are available at https: //github.com/yaoyao-yaoyao-cell/CRCG. We construct a novel synthetic graph dataset, CRCG, with inherent causal relationships and controllability. We evaluated our method on various datasets including: 1) Graph-SST5 (Yuan et al. 2023), 2) Graph-Twitter (Yuan et al. 2023), and 3) Spurious-Motif (Wu et al. 2022) under different bias, 4) our proposed CRCG. |
| Dataset Splits | No | The paper states, "The details of the experiment settings and dataset can be found in Appendix C.2 and C.3." However, the main text of the paper does not explicitly provide the training/validation/test dataset splits (e.g., percentages, counts, or explicit mention of standard splits with citations that include authors and years). |
| Hardware Specification | No | The paper mentions "CPU time overhead" in its computational cost analysis but does not provide specific details about the hardware used to run the experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | The paper mentions various methods and models (e.g., GNNs, ERM, ASAP, DIR, CIGA, RCGRL, DISC) and references related works, but it does not specify the versions of software libraries, programming languages (e.g., Python 3.x), or deep learning frameworks (e.g., PyTorch 1.x, TensorFlow 2.x) used for the implementation or experiments. |
| Experiment Setup | No | The paper states, "The details of the experiment settings and dataset can be found in Appendix C.2 and C.3." However, the main body of the paper does not explicitly provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed optimizer settings. |