Inhalt des Dokuments
Publikationen
| Zitatschlüssel | Papadias2020 |
|---|---|
| Autor | Serafeim Papadias |
| Jahr | 2020 |
| Journal | VLDB 2020 PhD Workshop |
| Notiz | A
recording of the presentation ist available here:
https://www.youtube.com/watch?v=kFx4yKWFY5E Presentation slides are available here: https://www.redaktion.tu-berlin.de/fileadmin/fg131/Conferences/Presentations/Papadias_VLDB-2020.pdf |
| Zusammenfassung | An increasing number of real-world applications require ma-chine learning tasks over large-scale streaming graphs, where nodes and edges are continuously being added or deleted. Graph embeddings have been widely used for solving such tasks by capturing the graph structure and features into a low-dimensional latent space. However, current approaches have one or more of the following disadvantages: (i) they are designed for either static or dynamic graphs and thus, need retraining after each graph change or periodically up-dating the embeddings after each snapshot arrival, (ii) they fail to scale to today’s size of graphs composed of billions of nodes, or (iii) yet the ones devised for streaming graphs perform redundant retraining computations by mandating continuous embedding updates even if the accuracy is not improved. The goal of this thesis is to overcome the above-mentioned problems by devising tunable streaming methods that can scale to massive graphs. We envision an end-to-end ML streaming system that achieves that goal and provides users with abstractions to easily define their own streaming embedding algorithms. |
Zurück [3]
[4]
ublikationen/parameter/de/font3/minhilfe/?no_cache=1&am
p;tx_sibibtex_pi1%5Bdownload_bibtex_uid%5D=10230370&
;tx_sibibtex_pi1%5Bcontentelement%5D=tt_content%3A12688
3
ublikationen/parameter/de/font3/minhilfe/
ig_data_management_report/parameter/de/font3/minhilfe/
Zusatzinformationen / Extras
Direktzugang:
Schnellnavigation zur Seite über Nummerneingabe
Hilfsfunktionen
Copyright TU Berlin 2008