Lunch at ICAI: Discovery & Perception in NL

This Lunch at ICAI session is focused on Discovery & Perception in The Netherlands. The Delta lab, collaboration with Bosch, and the Discovery Lab, collaboration with Elsevier, in Amsterdam will share their story. Two speakers highlight their recent work. And two leaders in the field point out future directions.

12.00 (noon): Herke van Hoof (University of Amsterdam) presents the Delta Lab
12.05: Victor Garcia: Inductive biases and message passing algorithms

12.20: Rinke Hoekstra (Elsevier) presents the Discovery Lab
12.25: Daniel Daza: Inductive Entity Representations from Text via Link Prediction

12.40: Herke van Hoof and Rinke Hoekstra discuss what's next in AI in The Netherlands and beyond
13.00: End

All times are CET.

Inductive biases and message passing algorithms
Message passing algorithms (e.g. graph neural networks) are becoming a very powerful tool in a wide variety of applications: Modelling dynamical systems, social networks, signal processing, molecular property prediction, drug discovery... In this talk we explore different methods to augment message passing algorithms with prior knowledge (e.g. human knowledge) and we show the resulting combination benefits in both performance and data efficiency.

Inductive Entity Representations from Text via Link Prediction
Knowledge Graphs are of vital importance for multiple applications on the web, including information retrieval, recommender systems, and metadata annotation. Regardless of whether they are built manually by domain experts or with automatic pipelines, such graphs are often incomplete. While some machine learning methods have been proposed to address this issue, many of them ignore properties like entity descriptions, and are limited to predictions involving entities in the training set.

In this talk, I will introduce our recently proposed method for link prediction over knowledge graphs where entities have an associated textual description. I will then describe our experimental framework and discuss how such a method enables learning representations of entities that are not limited to link prediction in the graph, but also to other tasks like entity classification and information retrieval.

----
Interested in listening to what research have to tell about the latest developments in AI. Listen to our podcast:
https://icai.ai/snoek-op-zolder-new-podcast-by-nl-aic-and-icai/

*** This is an online meeting. Make sure to (1) sign up for the meetup on the meetup page and (2) ensure you receive emails from Meetup. Shortly before the event we will send you the Zoom link to attend, as well as the info you need to log in via a web browser (if your organization does not allow you to install Zoom). You will only receive this if you have done both these steps. ***