%0 Conference Paper %1 guo_spine:_2019 %A Guo, Junliang %A Xu, Linli %A Liu, Jingchang %B Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence %C Macao, China %D 2019 %I International Joint Conferences on Artificial Intelligence Organization %K Embedding_Algorithm Node_Embeddings Skip-Gram %P 2399--2405 %R 10.24963/ijcai.2019/333 %T SPINE: Structural Identity Preserved Inductive Network Embedding %U https://www.ijcai.org/proceedings/2019/333 %X Recent advances in the field of network embedding have shown that low-dimensional network representation is playing a critical role in network analysis. Most existing network embedding methods encode the local proximity of a node, such as the first- and second-order proximities. While being efficient, these methods are short of leveraging the global structural information between nodes distant from each other. In addition, most existing methods learn embeddings on one single fixed network, and thus cannot be generalized to unseen nodes or networks without retraining. In this paper we present SPINE, a method that can jointly capture the local proximity and proximities at any distance, while being inductive to efficiently deal with unseen nodes or networks. Extensive experimental results on benchmark datasets demonstrate the superiority of the proposed framework over the state of the art. %@ 978-0-9992411-4-1

@inproceedings{guo_spine:_2019, abstract = {Recent advances in the field of network embedding have shown that low-dimensional network representation is playing a critical role in network analysis. Most existing network embedding methods encode the local proximity of a node, such as the first- and second-order proximities. While being efficient, these methods are short of leveraging the global structural information between nodes distant from each other. In addition, most existing methods learn embeddings on one single fixed network, and thus cannot be generalized to unseen nodes or networks without retraining. In this paper we present SPINE, a method that can jointly capture the local proximity and proximities at any distance, while being inductive to efficiently deal with unseen nodes or networks. Extensive experimental results on benchmark datasets demonstrate the superiority of the proposed framework over the state of the art.}, added-at = {2020-02-21T16:09:44.000+0100}, address = {Macao, China}, author = {Guo, Junliang and Xu, Linli and Liu, Jingchang}, biburl = {https://www.bibsonomy.org/bibtex/2c027366dcd194896160d154a76013ae9/tschumacher}, booktitle = {Proceedings of the {Twenty}-{Eighth} {International} {Joint} {Conference} on {Artificial} {Intelligence}}, doi = {10.24963/ijcai.2019/333}, file = {Guo et al - SPINE ~ Structural Identity Preserved Inductive Network Embedding.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Guo et al - SPINE ~ Structural Identity Preserved Inductive Network Embedding.pdf:application/pdf}, interhash = {14200a6af4c670ce9d9231d0f6b5db7a}, intrahash = {c027366dcd194896160d154a76013ae9}, isbn = {978-0-9992411-4-1}, keywords = {Embedding_Algorithm Node_Embeddings Skip-Gram}, language = {en}, month = aug, pages = {2399--2405}, publisher = {International Joint Conferences on Artificial Intelligence Organization}, shorttitle = {{SPINE}}, timestamp = {2020-02-21T16:09:44.000+0100}, title = {{SPINE}: {Structural} {Identity} {Preserved} {Inductive} {Network} {Embedding}}, url = {https://www.ijcai.org/proceedings/2019/333}, urldate = {2019-12-10}, year = 2019 }