Graph Neural Networks for Knowledge Representation and Recommendation
by Max Welling
Graph Neural Networks have gained enormous popularity in recent years and found widespread application in, among others, physics and chemistry, computer vision, simulation, healthcare, wireless communication, logistics, natural language processing, causality, knowledge representation and recommendation. In this talk I will give a brief introduction on graph neural networks and their relation to deep learning. I will also discuss how to incorporate symmetries in GNNs and discuss a number of applications on which I have worked. In the last part of the talk I will discuss in a little bit more detail how GNNs can be applied to KR, IR and recommender systems.
About the speaker
Max Welling is a research chair in Machine Learning at the University of Amsterdam and a Distinguished Scientist at MSR. He is a fellow at the Canadian Institute for Advanced Research (CIFAR) and the European Lab for Learning and Intelligent Systems (ELLIS) where he also serves on the founding board. His previous appointments include VP at Qualcomm Technologies, professor at UC Irvine, postdoc at U. Toronto and UCL under supervision of Prof. Geoffrey Hinton, and postdoc at Caltech under supervision of prof. Pietro Perona. He finished his PhD in theoretical high energy physics under supervision of Nobel laureate Prof. Gerard ‘t Hooft.
Max Welling has served as associate editor in chief of IEEE TPAMI from 2011-2015, he serves on the advisory board of the NeurIPS foundation since 2015 and has been program chair and general chair of NeurIPS in 2013 and 2014 respectively. He was also program chair of AISTATS in 2009 and ECCV in 2016 and general chair of MIDL 2018. Max Welling is recipient of the ECCV Koenderink Prize in 2010 and the ICML Test of Time award in 2021. He directs the Amsterdam Machine Learning Lab (AMLAB) and co-directs the Qualcomm-UvA deep learning lab (QUVA) and the Bosch-UvA Deep Learning lab (DELTA).
Date
Monday, Sept 27, 14:00-14:45
Regulating Recommenders
by Natali Helberger
Recommenders are the power engines of the digital society. They order and unlock information online, manage our attention, make and break businesses and control the constant flow of information and disinformation. So much power over markets and society cannot escape the attention of regulators, and in the past year the European Commission has launched into a series of ambitious initiatives to set a (world-wide) standard of dealing with the potential risks and opportunities of recommendation algorithms. While the draft Digital Services Act and the Digital Markets Act very much focus on recommenders controlled by Very Large Online Platform, other initiatives such as the draft AI Regulation or the Data Governance Act pertain to setting the conditions for the operation of recommenders more broadly. In my presentation I will map this emerging landscape of rules and regulations and offer some critical reflections of how they will shape recommender design in the years to come.
About the speaker
Natali Helberger is Distinguished University Professor of Law and Digital Technology with a special focus on AI at the University of Amsterdam and a member of the board of directors of the Institute for Information Law (IViR), one of the leading information law institutes worldwide. Her research over the past five years has focused on how AI and automated decision making are transforming society and their implications for law and governance. She was awarded an ERC grant for her research about the legal and democratic implications of recommender systems (PersoNews). Together with Prof. Dr. Claes de Vreese, Helberger founded the Research Priority Area Information, Communication, and the Data Society (www.uva-icds.net) at the University of Amsterdam, which has pioneered methods to study the societal impact of digital technologies and shaped the international discussion on filter bubbles, platform governance, data-driven communication, and political micro-targeting. She is also one of the founders of the AI, Media & Democracy Lab that brings together media professionals and researchers to research, develop and test AI applications in the media. Natali is regularly asked to advise national and European law makers and regulatory authorities, and is the chair of the Council of Europe Committee on AI and Freedom of Expression.
Date
Tuesday, Sept 28, 14:00-14:45
Key notes from keys and notes: pianist perspectives on recommendation
by Cynthia Liem
photo: Marco Borggreve all rights reserved
A recommender makes choices on what—or whom—to promote or deprioritize. In this keynote, I consider this challenge through the different perspectives that I have taken professionally: as a technologist, as earlier-career faculty, but particularly, as a performing artist. Over the past centuries, the perception, reception and promotion of classical music has been evolving and changing. Looking at this more closely raises some interesting questions on how we currently conceptualize our recommender systems, and especially, how we establish and sustain ‘what is worth promoting’. As I will argue, going back to Bach and bel canto can be of inspiration in rethinking our future technologies, as well as our own professional roles.
About the speaker
Cynthia C. S. Liem is an Associate Professor in the Multimedia Computing Group of Delft University of Technology, The Netherlands, and pianist of the Magma Duo. Her research interests focus on making people discover new interests and content which would not trivially be retrieved, and assessing questions of validation and validity, especially in the context of music and multimedia search and recommendation. She initiated and co-coordinated the European research projects PHENICX (2013-2016) and TROMPA (2018-2021), focusing on technological enrichment of digital musical heritage, gained industrial experience at Bell Labs Netherlands, Philips Research and Google, and served as general co-chair of the 20th anniversary edition of the International Society for Music Information Retrieval (ISMIR) conference in 2019. She was a recipient of the Lucent Global Science and Google Anita Borg Europe Memorial scholarships, the Google European Doctoral Fellowship 2010 in Multimedia, a finalist of the New Scientist Science Talent Award 2016 for young scientists committed to public outreach, and is a member of the Dutch national Young Academy (2021-2026). This year, she is serving as Inclusion and Accessibility Chair at RecSys 2021.
Date
Wednesday, Sept 29, 14:00-14:45
