Aligning Users across Social Networks Using Network Embedding

Authors: Li Liu, William K. Cheung, Xin Li, Lejian Liao

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on real social network datasets demonstrate the effectiveness and efficiency of the proposed approach compared with several state-of-the-art methods.
Researcher Affiliation Academia 1 BJ ER Center of HVLIP&CC, School of Comp. Sci., Beijing Institute of Technology, Beijing, China 2 Department of Computer Science, Hong Kong Baptist University, Hong Kong, China
Pseudocode Yes Algorithm 1: Learning Aligned IONE Across Networks
Open Source Code No The paper does not provide any statement or link indicating the public release of source code for the methodology described.
Open Datasets Yes For performance evaluation, we employ two real-world social network datasets collected from Foursquare and Twitter [Zhang and Yu, 2015a].
Dataset Splits No The paper mentions "training-to-test ratios" and "training sets" but does not provide specific percentages or counts for training, validation, or test splits needed to reproduce the data partitioning of the main model. It only implicitly refers to varying training ratios in Fig 2(b) without specifying values in the text itself for the IONE.
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions algorithms used (e.g., "stochastic gradient descent", "negative sampling", "SVM-Platt scaling classification model") but does not specify any software libraries or their version numbers.
Experiment Setup Yes Algorithm 1: Learning Aligned IONE Across Networks... Require: Two networks GX and GY , a set of anchor links Ea, learning rate , # of negative samples K