Wednesday, 5th April 2023 - 4pm Mikhail Galkin : Seminar Title: Towards Neural Graph Databases Abstract: Graph databases are workhorses behind many industrial applications thanks to a flexible graph data model that can be efficiently queried. Still, with the growing sizes of graphs the incompleteness grows simultaneously and symbolic DBs can't easily cope with that without sacrificing performance or decidability. On the other hand, neural graph reasoning methods are designed for incomplete graphs and performing link prediction in the latent space. The most recent development in graph reasoning is complex logical query answering able to answer database-like complex queries in the latent space without explicit DB indexes and engines. In this talk, we will discuss the concept of Neural Graph Databases, their design agenda, and survey a few methods that can potentially be the engine of such systems. Bio: Michael is a Research Scientist at Intel AI Labs working on Graph Machine Learning and Geometric Deep Learning. Previously, Michael was a postdoc at Mila - Quebec AI Institute working with Will Hamilton, Jian Tang, and Reihaneh Rabbany on various graph learning tasks ranging from reasoning and knowledge graphs to molecular representation learning. Add to your calendar vCal iCal Apr 05 2023 16.00 - 17.00 Wednesday, 5th April 2023 - 4pm Mikhail Galkin : Seminar This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk. Online invitation only Contact
Wednesday, 5th April 2023 - 4pm Mikhail Galkin : Seminar Title: Towards Neural Graph Databases Abstract: Graph databases are workhorses behind many industrial applications thanks to a flexible graph data model that can be efficiently queried. Still, with the growing sizes of graphs the incompleteness grows simultaneously and symbolic DBs can't easily cope with that without sacrificing performance or decidability. On the other hand, neural graph reasoning methods are designed for incomplete graphs and performing link prediction in the latent space. The most recent development in graph reasoning is complex logical query answering able to answer database-like complex queries in the latent space without explicit DB indexes and engines. In this talk, we will discuss the concept of Neural Graph Databases, their design agenda, and survey a few methods that can potentially be the engine of such systems. Bio: Michael is a Research Scientist at Intel AI Labs working on Graph Machine Learning and Geometric Deep Learning. Previously, Michael was a postdoc at Mila - Quebec AI Institute working with Will Hamilton, Jian Tang, and Reihaneh Rabbany on various graph learning tasks ranging from reasoning and knowledge graphs to molecular representation learning. Add to your calendar vCal iCal Apr 05 2023 16.00 - 17.00 Wednesday, 5th April 2023 - 4pm Mikhail Galkin : Seminar This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk. Online invitation only Contact
Apr 05 2023 16.00 - 17.00 Wednesday, 5th April 2023 - 4pm Mikhail Galkin : Seminar This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk.
