DANE: Domain Adaptive Network Embedding
Authors: Yizhou Zhang, Guojie Song, Lun Du, Shuwen Yang, Yilun Jin
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments reflect that the proposed framework outperforms other well-recognized network embedding baselines in cross-network domain adaptation tasks. |
| Researcher Affiliation | Academia | 1School of Electronic Engineering and Computer Science, Peking University 2Key Laboratory of Machine Perception (Ministry of Education), Peking University {zhangyizhou2015, dulun, gjsong, swyang, yljin}@pku.edu.cn |
| Pseudocode | No | The paper describes the methodology using prose and mathematical equations but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code or provide links to a code repository. |
| Open Datasets | Yes | Paper Citation Networks1 consist of two different networks A and B, where each node is a paper... 1collected from Aminer database [Tang, 2016] |
| Dataset Splits | No | The paper describes using a source network for training and a target network for testing in a domain adaptation context. However, it does not explicitly provide details for a separate validation split within these networks or for hyperparameter tuning. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments, such as GPU or CPU models. |
| Software Dependencies | No | The paper mentions general software components like 'L2-regularized logistic regression via SGD algorithm' and 't-SNE package' but does not specify any version numbers for these or other software dependencies. |
| Experiment Setup | Yes | To be fair, for all methods we set the embedding dimension to 128 on Paper Citation Networks, and 32 on Co-author Networks. For methods applying negative sampling, we set negative sampling number as 5. For methods employing GCN, we use same activation function and 2-layer architecture. |