Keynote Speakers 2023
Keynote Speaker Ⅰ
Prof. Jan Peters
TU Darmstadt, German Research Center for AI (DFKI), Hessian.AI, Germany
IEEE Fellow, ELLIS Fellow and AAIA Fellow
Introduction to Prof. Jan Peters:
Jan Peters is a full professor (W3) for Intelligent Autonomous Systems at the Computer Science Department of the Technische Universitaet Darmstadt since 2011, and, at the same time, he is the dept head of the research department on Systems AI for Robot Learning (SAIROL) at the German Research Center for Artificial Intelligence (Deutsches Forschungszentrum für Künstliche Intelligenz, DFKI) since 2022. He is also is a founding research faculty member of the Hessian Center for Artificial Intelligence. Jan Peters has received the Dick Volz Best 2007 US PhD Thesis Runner-Up Award, the Robotics: Science & Systems - Early Career Spotlight, the INNS Young Investigator Award, and the IEEE Robotics & Automation Society's Early Career Award as well as numerous best paper awards. In 2015, he received an ERC Starting Grant and in 2019, he was appointed IEEE Fellow, in 2020 ELLIS fellow and in 2021 AAIA fellow. Despite being a faculty member at TU Darmstadt only since 2011, Jan Peters has already nurtured a series of outstanding young researchers into successful careers. These include new faculty members at leading universities in the USA, Japan, Germany, Finland and Holland, postdoctoral scholars at top computer science departments (including MIT, CMU, and Berkeley) and young leaders at top AI companies (including Amazon, Boston Dynamics, Google and Facebook/Meta). Jan Peters has studied Computer Science, Electrical, Mechanical and Control Engineering at TU Munich and FernUni Hagen in Germany, at the National University of Singapore (NUS) and the University of Southern California (USC). He has received four Master's degrees in these disciplines as well as a Computer Science PhD from USC. Jan Peters has performed research in Germany at DLR, TU Munich and the Max Planck Institute for Biological Cybernetics (in addition to the institutions above), in Japan at the Advanced Telecommunication Research Center (ATR), at USC and at both NUS and Siemens Advanced Engineering in Singapore. He has led research groups on Machine Learning for Robotics at the Max Planck Institutes for Biological Cybernetics (2007-2010) and Intelligent Systems (2010-2021).
Inductive Biases for Robot Learning
Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can learn tasks triggered by environmental context or higher level instruction. However, learning techniques have yet to live up to this promise as only few methods manage to scale to high-dimensional manipulator or humanoid robots. In this talk, we investigate a general framework suitable for learning motor skills in robotics which is based on the principles behind many analytical robotics approaches. To accomplish robot reinforcement learning learning from just few trials, the learning system can no longer explore all learn-able solutions but has to prioritize one solution over others – independent of the observed data. Such prioritization requires explicit or implicit assumptions, often called ‘induction biases’ in machine learning. Extrapolation to new robot learning tasks requires induction biases deeply rooted in general principles and domain knowledge from robotics, physics and control. Empirical evaluations on a several robot systems illustrate the effectiveness and applicability to learning control on an anthropomorphic robot arm. These robot motor skills range from toy examples (e.g., paddling a ball, ball-in-a-cup) to playing robot table tennis, juggling and manipulation of various objects.
Keynote Speaker Ⅱ
Prof. Guandong Xu
University of Technology Sydney, Australia
IET Fellow and ACS Fellow
Introduction to Prof. Guandong Xu:
Dr Guandong Xu is a Professor in the School of Computer Science and Data Science Institute at UTS and an award-winning researcher working in the fields of data mining, machine learning, social computing and other associated fields. Guandong is the Director of the UTS-Providence Smart Future Research Centre, which targets research and innovation in disruptive technology to drive sustainability. His research has attracted funding of more than $8 million from the ARC, government and industry. He also heads the Data Science and Machine Intelligence Lab, which is dedicated to research excellence and industry innovation across academia and industry, aligning with the UTS research priority areas in data science and artificial intelligence. Guandong has had more than 240 papers published in the fields of Data Science and Data Analytics, Recommender Systems, Text Mining, Predictive Analytics, User Behaviour Modelling, and Social Computing in international journals and conference proceedings in recent years, with increasing citations from academia. He has won numerous awards, including the Digital Disruptors Winner for ICT Research Project of the Year, Australian Computer Society (2021), the eBay's Leaders' Choice Award (2021); the CIKM'2021 Conference Best Research Paper Finalist; Global Efma-Accenture Insurance Innovation Award in Workforce Transformation (2020); the Digital Disruptors Winner for Skills Transformation of Small Work Teams, Australian Computer Society (2019), and the Digital Disruptors Gold Award of Service Transformation for the Digital Consumer – Corporate by Australian Computer Society (2019); the Top 10 Analytics Leaders by Australian Analytics Professional Peak Body (2018); the Australasian Database Conference Best Student Paper Award (2018); Marketing Excellence Award in Customer Research, NSW (2017), and; the Big Insights Data Innovation Award in Customer Insights (2016). He has shown strong academic leadership in various professional activities. He is the founding Editor-in-Chief of Human-centric Intelligent Systems Journal, the Assistant Editor-in-Chief of World Wide Web Journal, as well as the founding Steering Committee Chair of the International Conference of Behavioural and Social Computing Conference. Guandong has an MSc and a BSc in Computer Science and Engineering, and a PhD in Computer Science. After holding various research positions at European and Australian universities, he joined UTS in 2012. He was elected as the Fellow of Institution of Engineering and Technology (IET), UK and the Fellow of Australian Computer Society (ACS) in 2021 and 2022.
Counterfactual Explanations in Conversational Recommendation
Conversational Recommender Systems (CRSs) fundamentally differ from traditional recommender systems by interacting with users in a conversational session to accurately predict their current preferences and provide personalized recommendations. Although current CRSs have achieved favorable recommendation performance, the explainability is still in its infancy stage. Most of the CRSs tend to provide coarse explanations and fail to explore the impact of minimal alterations on the recommendation decisions on items. In this talk, we propose to incorporate the counterfactual techniques into CRS and propose a Counterfactual Explainable Conversational Recommender (CECR) to enhance the recommendation model from a counterfactual perspective. Counterfactual explanations can offer finegrained reasons to explain users’ realime intentions, meanwhile generating counterfactual samples for augmenting the training dataset to enhance recommendation performance. Specifically, CECR adaptively learns users’ preferences based on the conversation context and effectively responds to users’ realtime feedback during multiple rounds of conversation. Empirical experiments carried out on three benchmark datasets show that our CECR outperforms state-of-the-art CRSs in terms of recommendation performance and explainability.