Dynamic Network Embedding : An Extended Approach for Skip-gram based Network Embedding
L. Du, Y. Wang, G. Song, Z. Lu, and J. Wang. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, page 2086--2092. Stockholm, Sweden, International Joint Conferences on Artificial Intelligence Organization, (July 2018)
DOI: 10.24963/ijcai.2018/288
Abstract
Network embedding, as an approach to learn lowdimensional representations of vertices, has been proved extremely useful in many applications. Lots of state-of-the-art network embedding methods based on Skip-gram framework are efficient and effective. However, these methods mainly focus on the static network embedding and cannot naturally generalize to the dynamic environment. In this paper, we propose a stable dynamic embedding framework with high efficiency. It is an extension for the Skip-gram based network embedding methods, which can keep the optimality of the objective in the Skip-gram based methods in theory. Our model can not only generalize to the new vertex representation, but also update the most affected original vertex representations during the evolvement of the network. Multi-class classification on three real-world networks demonstrates that, our model can update the vertex representations efficiently and achieve the performance of retraining simultaneously. Besides, the visualization experimental result illustrates that, our model is capable of avoiding the embedding space drifting.
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
year
2018
month
jul
pages
2086--2092
publisher
International Joint Conferences on Artificial Intelligence Organization
shorttitle
Dynamic Network Embedding
isbn
978-0-9992411-2-7
language
en
file
Du et al - Dynamic Network Embedding ~ An Extended Approach for Skip-gram based Network Embedding.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Du et al - Dynamic Network Embedding ~ An Extended Approach for Skip-gram based Network Embedding.pdf:application/pdf
%0 Conference Paper
%1 du_dynamic_2018
%A Du, Lun
%A Wang, Yun
%A Song, Guojie
%A Lu, Zhicong
%A Wang, Junshan
%B Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
%C Stockholm, Sweden
%D 2018
%I International Joint Conferences on Artificial Intelligence Organization
%K Dynamic_Graphs Embedding_Algorithm Node_Embeddings Skip-Gram
%P 2086--2092
%R 10.24963/ijcai.2018/288
%T Dynamic Network Embedding : An Extended Approach for Skip-gram based Network Embedding
%U https://www.ijcai.org/proceedings/2018/288
%X Network embedding, as an approach to learn lowdimensional representations of vertices, has been proved extremely useful in many applications. Lots of state-of-the-art network embedding methods based on Skip-gram framework are efficient and effective. However, these methods mainly focus on the static network embedding and cannot naturally generalize to the dynamic environment. In this paper, we propose a stable dynamic embedding framework with high efficiency. It is an extension for the Skip-gram based network embedding methods, which can keep the optimality of the objective in the Skip-gram based methods in theory. Our model can not only generalize to the new vertex representation, but also update the most affected original vertex representations during the evolvement of the network. Multi-class classification on three real-world networks demonstrates that, our model can update the vertex representations efficiently and achieve the performance of retraining simultaneously. Besides, the visualization experimental result illustrates that, our model is capable of avoiding the embedding space drifting.
%@ 978-0-9992411-2-7
@inproceedings{du_dynamic_2018,
abstract = {Network embedding, as an approach to learn lowdimensional representations of vertices, has been proved extremely useful in many applications. Lots of state-of-the-art network embedding methods based on Skip-gram framework are efficient and effective. However, these methods mainly focus on the static network embedding and cannot naturally generalize to the dynamic environment. In this paper, we propose a stable dynamic embedding framework with high efficiency. It is an extension for the Skip-gram based network embedding methods, which can keep the optimality of the objective in the Skip-gram based methods in theory. Our model can not only generalize to the new vertex representation, but also update the most affected original vertex representations during the evolvement of the network. Multi-class classification on three real-world networks demonstrates that, our model can update the vertex representations efficiently and achieve the performance of retraining simultaneously. Besides, the visualization experimental result illustrates that, our model is capable of avoiding the embedding space drifting.},
added-at = {2020-02-21T16:09:44.000+0100},
address = {Stockholm, Sweden},
author = {Du, Lun and Wang, Yun and Song, Guojie and Lu, Zhicong and Wang, Junshan},
biburl = {https://www.bibsonomy.org/bibtex/2defdf9abb1bea3244e852cf78b55b950/tschumacher},
booktitle = {Proceedings of the {Twenty}-{Seventh} {International} {Joint} {Conference} on {Artificial} {Intelligence}},
doi = {10.24963/ijcai.2018/288},
file = {Du et al - Dynamic Network Embedding ~ An Extended Approach for Skip-gram based Network Embedding.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Du et al - Dynamic Network Embedding ~ An Extended Approach for Skip-gram based Network Embedding.pdf:application/pdf},
interhash = {a72486ee8c1755a35b2041d1d5f02435},
intrahash = {defdf9abb1bea3244e852cf78b55b950},
isbn = {978-0-9992411-2-7},
keywords = {Dynamic_Graphs Embedding_Algorithm Node_Embeddings Skip-Gram},
language = {en},
month = jul,
pages = {2086--2092},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
shorttitle = {Dynamic {Network} {Embedding}},
timestamp = {2020-02-21T16:09:44.000+0100},
title = {Dynamic {Network} {Embedding} : {An} {Extended} {Approach} for {Skip}-gram based {Network} {Embedding}},
url = {https://www.ijcai.org/proceedings/2018/288},
urldate = {2019-12-10},
year = 2018
}