Max-Margin DeepWalk: Discriminative Learning of Network Representation
Authors: Cunchao Tu, Weicheng Zhang, Zhiyuan Liu, Maosong Sun
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The visualizations of learnt representations indicate that our model is more discriminative than unsupervised ones, and the experimental results on vertex classification demonstrate that our method achieves a significant improvement than other state-of-the-art methods. |
| Researcher Affiliation | Academia | Cunchao Tu1,2 , Weicheng Zhang3 , Zhiyuan Liu1,2 , Maosong Sun1,2 1Department of Computer Science and Technology, State Key Lab on Intelligent Technology and Systems, National Lab for Information Science and Technology, Tsinghua University, Beijing, China 2Jiangsu Collaborative Innovation Center for Language Ability, Jiangsu Normal University, Xuzhou, China 3Beijing University of Posts and Telecommunications, China |
| Pseudocode | No | The paper describes the optimization algorithm but does not present it in a formal pseudocode block or algorithm listing. |
| Open Source Code | Yes | The source code can be obtained from https://github. com/thunlp/MMDW. |
| Open Datasets | Yes | Cora. Cora2 is a research paper set constructed by [Mc Callum et al., 2000]. Citeseer is another research paper set constructed by [Mc Callum et al., 2000]. Wiki [Sen et al., 2008] contains 2, 405 web pages from 19 categories and 17, 981 links between them. |
| Dataset Splits | Yes | For evaluation, we randomly sample a portion of labeled vertices and take their representations as features for training, and the rest are used for testing. We increase the training ratio from 10% to 90%, and employ multi-class SVM [Crammer and Singer, 2002] to build classifiers. |
| Hardware Specification | No | The paper does not specify any hardware used for the experiments (e.g., GPU/CPU models, memory). |
| Software Dependencies | No | The paper mentions several models and tools (Deep Walk, LINE, Skip-Gram, SVM, t-SNE) but does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | We set parameters in Deep Walk as follows, window size K = 5, walks per vertex γ = 80 and representation dimension k = 200. We also show the performance of MMDW with ranging from 10 4 to 10 2. |