Representation Learning for Scale-Free Networks

Authors: Rui Feng, Yang Yang, Wenjie Hu, Fei Wu, Yueting Zhang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on six datasets show that our algorithms are able to not only reconstruct heavy-tailed distributed degree distribution, but also outperform state-ofthe-art embedding models in various network mining tasks, such as vertex classification and link prediction.
Researcher Affiliation Academia College of Computer Science and Technology, Zhejiang University, China
Pseudocode No The paper describes algorithms using text and mathematical equations, but does not include formal pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement or link regarding the availability of open-source code for the described methodology.
Open Datasets Yes Facebook (Leskovec and Mcauley 2012): This dataset is a subnetwork of Facebook. Twitter (Leskovec and Mcauley 2012): This dataset is a subnetwork of Twitter. Coauthor (Leskovec, Kleinberg, and Faloutsos 2007): This network covers scientific collaborations between authors. Citation (Tang et al. 2008): Similar to Coauthor, this is also an academic network, where vertexes are authors.
Dataset Splits No For link prediction, the paper states 'randomly select about 1% pairs of vertexes for training and evaluation', but does not specify a train/validation/test split or provide percentages/counts.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models) used to run the experiments.
Software Dependencies No The paper refers to methods like 'word2vec', 'Deep Walk', and 'node2vec' and mentions 'Hierarchical Softmax' for implementation, but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes Unless otherwise specified, the embedding dimension for our experiments is 200. Specifically, we perform 10 random walks starting from each vertex, and each random walk will have a length of 40. In our proposed models, β R is the model parameter used to indicate the strength of degree penalty.