Keynote I - User-Item Matching and
Auto-encoders for Cold-start Next-Item Recommendation
Dr. Michael Ng
Professor, Department of Mathematics, The University of Hong
Recommendation systems provide personalized service to users and aim at
suggesting to them items that they may prefer. There is an increasing
requirement of next-item recommendation systems to infer a user’s next
favor item based on his/her historical selection of items. In this talk,
we study the next-item recommendation under the cold-start situation,
where the users in the system share no interaction with the new items.
We propose and study a novel model called User-Item Matching and
Auto-encoders, which learns the latent embeddings for both users and
items by exploiting user historical preferences and item attributes. The
relevant hypergraph collaborative networks will also be discussed in the
Michael Ng is a Chair Professor, Department of Mathematics, The
University of Hong Kong. He is elected as a SIAM Fellow in 2020, and won
the 12th Feng Kang Scientific Computing Prize in the same year to honor
his outstanding contributions to solving structured linear systems in
numerical linear algebra, mathematics and calculation methods in image
processing. He is the world's Top 2% most-cited scientists, HKU Scholars
in the Top 1%. His research interests including Applied and
Computational Mathematics, Artificial Intelligence and Machine Learning,
Data and Imaging Sciences and Scientific Computing.
Keynote II - Interactions of agents
in virtual societies: how they learn, what we learn, and what is
Dr. Ho-fung Leung
Professor, Department of Computer Science and Engineering, CUHK
Professor (by courtesy), Department of Sociology, CUHK
Interactions in Multiagent Systems has been one of the active research
areas in Artificial Intelligence. It studies ‘intelligent agents’ and
their interactions in ‘multi-agent systems,’ such as the phenomenon of
norm emergence as a result of multiagent learning in multiagent systems.
In the process of interaction, agents learn how to better interact with
other agents through their own experiences, which leads to changes in
individual and global behaviours. In this talk I shall start by
introducing the concept of intelligent agents, and how they learn and
adapt in interactions. I shall also explore what we learn from these
agent simulation experiments, using some research works done by us in
the recent years for illustration. Finally, I shall introduce our recent
work on mathematical modelling of the dynamics of the systems.
Professor Ho-fung Leung is a Professor in the Department of Computer
Science and Engineering and a Professor (by courtesy) in the Department
of Sociology at The Chinese University of Hong Kong. He is the Director
of the MSc Programme in Computer Science. His research interests cover
various aspects centring around artificial intelligence, including
multiagent systems (reinforcement learning, emergence phenomena, and
evolution dynamics), game theoretic analysis, ontologies (knowledge
graphs), and big data analytics. Professor Leung has authored more than
250 publications, including 5 research monographs, and 5 edited volumes.
Professor Leung was the chairperson of ACM (Hong Kong Chapter) in 1998.
He is a Chartered Fellow of the BCS, a Fellow of the HKIE, and a full
member the HKCS. He is a Chartered Engineer registered by the
Professor Leung received his BSc and MPhil degrees in Computer Science
from The Chinese University of Hong Kong, and his PhD degree from
University of London with DIC (Diploma of Imperial College) in Computing
from Imperial College London.