Learning Stochastic Equivalence based on Discrete Ricci Curvature
Authors: Xuan Guo, Qiang Tian, Wang Zhang, Wenjun Wang, Pengfei Jiao
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The effectiveness of our proposed CNESE is demonstrated by extensive experiments on realworld networks. |
| Researcher Affiliation | Academia | 1College of Intelligence and Computing, Tianjin University, Tianjin, China 2Center of Biosafety Research and Strategy, Law School, Tianjin University, Tianjin, China {guoxuan, tianqiang, wangzhang, wjwang, pjiao}@tju.edu.cn |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | Yes | 1https://github.com/cspjiao/CNESE |
| Open Datasets | Yes | We conduct the role-based node classification experiments on Air-traffic networks (USA, Brazil, and Europe) [Ribeiro et al., 2017], Actor co-occurrence network [Ma et al., 2019], Reality phone call network [Guo et al., 2020], and Enron email network [Klimt and Yang, 2004]. |
| Dataset Splits | No | The paper specifies a 70% training set and the rest as test set, but does not explicitly mention a separate validation split or its details. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory). |
| Software Dependencies | No | The paper mentions 'Adam SGD optimizer' but does not specify version numbers for any software dependencies or libraries (e.g., Python, PyTorch, TensorFlow). |
| Experiment Setup | Yes | The bin number of curvature histograms is set to 80. The width of MLPs and embedding dimension are set to 64. We apply Adam SGD optimizer [Kingma and Ba, 2015] with learning rate 0.001 and batch size 32 for at most 50 epochs. L2 regularization with weight 0.001 is adopted to avoid overfitting. In later experiments, unless otherwise stated, parameter α of α-Ricci-curvature is set as 0.05, and 0.5 on Brazil and the other datasets respectively. β is set to 5 and γ is set to and 2. |