Hybrid-order Stochastic Block Model

Authors: Xunxun Wu, Chang-Dong Wang, Pengfei Jiao4470-4477

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on six real-world datasets show that the proposed method outperforms the existing approaches.
Researcher Affiliation Academia Xunxun Wu,1 Chang-Dong Wang, 1,2,3* Pengfei Jiao 4 1 School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China 2 Guangdong Province Key Laboratory of Computational Science, Guangzhou, China 3 Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China 4 Center of Biosafety Research and Strategy, Law school of Tianjin University, Tianjin, China
Pseudocode Yes Algorithm 1 Hybrid-order Stochastic Block Model
Open Source Code No The paper does not provide any explicit statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets Yes Six widely used real-world datasets are adopted to test the effectiveness of the proposed method. Karete Club1: A social network about karate clubs composed of 34 nodes and 78 edges, and the nodes are divided into 2 communities. Polbooks1: A book network about US politics composed of 105 nodes and 441 edges, and the nodes are divided into 3 communities. Polblogs1: A network of hyperlinks between weblogs on US politics composed of 1490 nodes and 19090 edges, and the nodes are divided into 2 communities. Dolphins1: A dolphin social network of frequent associations composed of 62 nodes and 159 edges, and the nodes are divided into 2 communities. Football1: A social network about the American college football league composed of 115 nodes and 616 edges, and the nodes are divided into 12 communities. DBLP2: A paper cooperative network, which is a subset of DBLP dataset, containing 1163 nodes and 1392 edges, and the nodes are divided into 3 communities. 1http://www-personal.umich.edu/ mejn/netdata/ 2http://snap.stanford.edu/data/
Dataset Splits No The paper mentions 'ground-truth communities' for evaluation metrics like NMI and F1-Score, and discusses 'Extensive experiments on six real-world datasets' but does not specify details regarding training, validation, or testing splits (e.g., percentages, methodology, or specific files).
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments.
Software Dependencies No The paper does not provide specific version numbers for any software components, libraries, or solvers used in the experiments.
Experiment Setup No The paper mentions proposing a 'heuristic algorithm to optimize the objective function' but does not provide specific details on hyperparameters, initialization strategies, or system-level training configurations necessary for reproduction.