@article{kazemi_representation_2019,
	title = {Representation {Learning} for {Dynamic} {Graphs}: {A} {Survey}},
	shorttitle = {Representation {Learning} for {Dynamic} {Graphs}},
	url = {http://arxiv.org/abs/1905.11485},
	abstract = {Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets and highlight directions for future research.},
	urldate = {2021-01-16},
	journal = {arXiv:1905.11485 [cs, stat]},
	author = {Kazemi, Seyed Mehran and Goel, Rishab and Jain, Kshitij and Kobyzev, Ivan and Sethi, Akshay and Forsyth, Peter and Poupart, Pascal},
	month = may,
	year = {2019},
	note = {ZSCC: 0000018 
arXiv: 1905.11485
version: 1},
	keywords = {⛔ No DOI found, 表示学习},
}

{"_id":"sy4uehJYibnS9raoE","bibbaseid":"kazemi-goel-jain-kobyzev-sethi-forsyth-poupart-representationlearningfordynamicgraphsasurvey-2019","author_short":["Kazemi, S. M.","Goel, R.","Jain, K.","Kobyzev, I.","Sethi, A.","Forsyth, P.","Poupart, P."],"bibdata":{"bibtype":"article","type":"article","title":"Representation Learning for Dynamic Graphs: A Survey","shorttitle":"Representation Learning for Dynamic Graphs","url":"http://arxiv.org/abs/1905.11485","abstract":"Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets and highlight directions for future research.","urldate":"2021-01-16","journal":"arXiv:1905.11485 [cs, stat]","author":[{"propositions":[],"lastnames":["Kazemi"],"firstnames":["Seyed","Mehran"],"suffixes":[]},{"propositions":[],"lastnames":["Goel"],"firstnames":["Rishab"],"suffixes":[]},{"propositions":[],"lastnames":["Jain"],"firstnames":["Kshitij"],"suffixes":[]},{"propositions":[],"lastnames":["Kobyzev"],"firstnames":["Ivan"],"suffixes":[]},{"propositions":[],"lastnames":["Sethi"],"firstnames":["Akshay"],"suffixes":[]},{"propositions":[],"lastnames":["Forsyth"],"firstnames":["Peter"],"suffixes":[]},{"propositions":[],"lastnames":["Poupart"],"firstnames":["Pascal"],"suffixes":[]}],"month":"May","year":"2019","note":"ZSCC: 0000018 arXiv: 1905.11485 version: 1","keywords":"⛔ No DOI found, 表示学习","bibtex":"@article{kazemi_representation_2019,\n\ttitle = {Representation {Learning} for {Dynamic} {Graphs}: {A} {Survey}},\n\tshorttitle = {Representation {Learning} for {Dynamic} {Graphs}},\n\turl = {http://arxiv.org/abs/1905.11485},\n\tabstract = {Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets and highlight directions for future research.},\n\turldate = {2021-01-16},\n\tjournal = {arXiv:1905.11485 [cs, stat]},\n\tauthor = {Kazemi, Seyed Mehran and Goel, Rishab and Jain, Kshitij and Kobyzev, Ivan and Sethi, Akshay and Forsyth, Peter and Poupart, Pascal},\n\tmonth = may,\n\tyear = {2019},\n\tnote = {ZSCC: 0000018 \narXiv: 1905.11485\nversion: 1},\n\tkeywords = {⛔ No DOI found, 表示学习},\n}\n\n","author_short":["Kazemi, S. M.","Goel, R.","Jain, K.","Kobyzev, I.","Sethi, A.","Forsyth, P.","Poupart, P."],"key":"kazemi_representation_2019","id":"kazemi_representation_2019","bibbaseid":"kazemi-goel-jain-kobyzev-sethi-forsyth-poupart-representationlearningfordynamicgraphsasurvey-2019","role":"author","urls":{"Paper":"http://arxiv.org/abs/1905.11485"},"keyword":["⛔ No DOI found","表示学习"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/wybert","dataSources":["TJkbwzD8s2wCxBy6Y"],"keywords":["⛔ no doi found","表示学习"],"search_terms":["representation","learning","dynamic","graphs","survey","kazemi","goel","jain","kobyzev","sethi","forsyth","poupart"],"title":"Representation Learning for Dynamic Graphs: A Survey","year":2019}