Multi-Facet Network Embedding: Beyond the General Solution of Detection and Representation
Authors: Liang Yang, Yuanfang Guo, Xiaochun Cao
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we empirically evaluate the performances of MNE via vertex classification. Besides, the parameters sensitivity is analyzed. Datasets. The experiments are conducted on Facebook100 dataset... |
| Researcher Affiliation | Academia | Liang Yang,1,2 Yuanfang Guo, Xiaochun Cao 2 2, 1School of Computer Science and Engineering, Hebei University of Technology 2State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences {yangliang, guoyuanfang, caoxiaochun}@iie.ac.cn |
| Pseudocode | Yes | Algorithm 1: Multifaceted Network Embedding |
| Open Source Code | No | The paper does not contain an explicit statement regarding the release of source code or a link to a code repository for the methodology described. |
| Open Datasets | Yes | The experiments are conducted on Facebook100 dataset (Traud, Mucha, and Porter 2012). |
| Dataset Splits | No | The paper states 'a portion of the users are randomly selected to be the training data, while the rest of users are employed as the testing data' and 'By fixing the training rate to be 9%', but does not explicitly mention a separate validation set or a three-way split (train/validation/test). |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions 'Liblinear' as the SVM classifier implementation but does not specify its version number or versions for any other software dependencies. |
| Experiment Setup | Yes | The hyperparameters of MNE are set as follows: balancing parameters λ = 0.3, α = 0.001, number of facets Z = 2, number of embedding dimensions for each facets Ki = 64 for i = 1, 2 (the total dimension K = Z Ki = 128) and proximity matrix M = Q. |