Overlapping Clustering Models, and One (class) SVM to Bind Them All

Authors: Xueyu Mao, Purnamrita Sarkar, Deepayan Chakrabarti

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on several simulated and real datasets show our algorithm (called SVM-cone) is both accurate and scalable.
Researcher Affiliation Academia Xueyu Mao, Purnamrita Sarkar, Deepayan Chakrabarti The University of Texas at Austin xmao@cs.utexas.edu, purna.sarkar@austin.utexas.edu, deepay@utexas.edu
Pseudocode Yes Algorithm 1 SVM-cone
Open Source Code No The paper does not provide an explicit statement about the release of source code for the SVM-cone method, nor does it include a link to a code repository.
Open Datasets Yes For networks, we used the 5 DBLP coauthorship networks1 (used in [20], where each ground truth community corresponds to a group of conferences on the same topic. We also use bipartite author-paper variants for these 5 networks. 1http://www.cs.utexas.edu/~xmao/coauthorship
Dataset Splits No The paper describes dataset generation parameters (e.g., 'We generate networks with n = 5000 nodes and K = 3 communities.') and sampling parameters, but it does not specify explicit training, validation, or test dataset splits needed for reproducibility.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU models, CPU types, or memory specifications) used for running the experiments.
Software Dependencies Yes We use Matlab R2018a built-in Gibbs Sampling function for learning topic models to learn the word by topic matrix, which should retain the characteristics of real data distributions.
Experiment Setup Yes We set Bii = 1 and Bij = 0.1 for all i = j. The default degree parameters for DCMMSB are as follows: for all nodes i that are predominantly in the j-th community (θij > 0.5), we set Γii to 0.3, 0.5, and 0.7 for the 3 respective communities; all other nodes have Γii = 1.