SPINE: Structural Identity Preserved Inductive Network Embedding
Authors: Junliang Guo, Linli Xu, Jingchang Liu
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental results on benchmark datasets demonstrate the superiority of the proposed framework over the state of the art. |
| Researcher Affiliation | Academia | Junliang Guo , Linli Xu and Jingchang Liu Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science and Technology, University of Science and Technology of China |
| Pseudocode | Yes | Algorithm 1 Rooted random walk sampling |
| Open Source Code | Yes | 1Code is avaliable at https://github.com/lemmonation/spine |
| Open Datasets | Yes | We test the proposed model on four benchmark datasets to measure its performance on real-world tasks, and one small scale social network to validate the structural identity preserved in the learned embeddings. For the node classification task, we test our method on Citation Networks [Yang et al., 2016], where nodes and edges represent papers and citations respectively. To test the performance of SPINE while generalizing across networks, we further include PPI [Stark et al., 2006], which consists of multiple networks corresponding to different human tissues. To measure the structural identity preserved in embeddings, we test SPINE on a subset of Facebook dataset [Leskovec and Krevl, 2014], denoted as FB-686 |
| Dataset Splits | Yes | For the transductive setting, we use the same scheme of training/test partition provided by Yang et al. [2016]. As for the inductive setting, on citation networks, we randomly remove 20%, 40%, 60% and 80% nodes and the corresponding edges, these nodes are then treated as test nodes with the remaining network as the training data. Meanwhile on the PPI network, we follow the same dataset splitting strategy as in [Hamilton et al., 2017], i.e., 20 networks for training, 2 for validation and 2 for testing, where the validation and testing networks remain unseen during training. |
| Hardware Specification | No | The paper mentions 'Time (Seconds)' in Figure 2 for running time comparison but does not provide any specific hardware details such as CPU/GPU models, processor types, or memory. |
| Software Dependencies | No | The paper does not provide specific software dependency details with version numbers (e.g., library names with versions). |
| Experiment Setup | Yes | For all the methods, the dimensionality of embeddings is set to 200. Algorithm 1 takes hyper-parameters k, m, l as input. Algorithm 2 takes the structural rate α as input. |