Learning Signed Network Embedding via Graph Attention
Authors: Yu Li, Yuan Tian, Jiawei Zhang, Yi Chang4772-4779
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results demonstrate the effectiveness of the proposed framework through signed link prediction task on several real-world signed network datasets. |
| Researcher Affiliation | Academia | Yu Li,1,5 Yuan Tian,2,4 Jiawei Zhang,3 Yi Chang2,5 1College of Computer Science and Technology, Jilin University, China 2School of Artificial Intelligence, Jilin University, China 3IFM Lab, Department of Computer Science, Florida State University, USA 4Key Laboratory of Bionic Engineering, Ministry of Education, China 5Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, China |
| Pseudocode | Yes | Algorithm 1 : Embedding Generation Process of SNEA. |
| Open Source Code | No | The paper provides links to the code for baseline methods (Si NE, SIDE, SGCN, Si GAT) in footnotes, but there is no explicit statement or link indicating that the source code for the proposed SNEA framework is available. |
| Open Datasets | Yes | We conduct experiments on four real-world signed networks to evaluate the effectiveness the proposed framework: Bitcoin-Alpha1, Bitcoin-OTC2, Epinions3 and Slashdot4. 1http://www.btc-alpha.com 2http://www.bitcoin-otc.com 3http://www.epinions.com 4http://www.slashdot.com |
| Dataset Splits | No | For signed link prediction task, we randomly select 80% links as training set to learn the node embeddings and utilize the remaining links as test set to evaluate the performance. |
| Hardware Specification | No | The paper does not provide any specific details regarding the hardware (e.g., GPU models, CPU types) used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'Xavier initialization' and 'Ada Grad' for training, but does not specify any software dependencies with version numbers (e.g., programming languages, libraries, or frameworks with their versions). |
| Experiment Setup | Yes | For a fair comparison, we set the final embedding dimension as 64 for all the methods. ... For SNEA, we set λ as 4. ... we use final node embeddings (i.e., U) of TSVD as the initial embeddings of SNEA model. |