In the first part of this talk, I will be describing recent research conducted in my group to tackle both the personalized and group recommendations problems, using Machine Learning and Social Choice Theory. More specifically, we build our (Bayesian) recommendation algorithms following the “you are what you consume” (Babas et al, 2013) principle, while a key novelty in our approach is the application of multiwinner voting rules to increase recommendations’ diversity and fairness.
We conduct a systematic experimental evaluation of our approaches by applying them on a real-world dataset of Points of Interest (POIs) in the popular touristic destination of Agios Nikolaos, Crete; also exploiting information collected via questionnaires from actual tourists visiting the city of Agios Nikolaos. Our experimental results (i) highlight the ability of our systems to successfully produce personalized recommendations that match the specific interests of a single user; (ii) confirm that the employment of prior knowledge regarding the preferences of tourists, based on their demographics, guides our recommender to avoid the cold-start problem; (iii) demonstrate that the use of multiwinner mechanisms allows for diverse recommendations with respect to travel-related features, and increased system performance in the case of limited user-system interactions; and (iv) show that the use of multiwinner mechanisms allows for fair group recommendations with respect to the well-known m-PROPORTIONALITY and m-ENVY-FREENESS metrics. Last but not least, our personalized Bayesian recommendation algorithm is incorporated in a real-world mobile tour-planning application for Agios Nikolaos, Crete.
In the second part of this talk, we shift our focus to a novel Smart Grid Flexibility Aggregation framework, encompassing a multiagent architecture and various types of mechanisms for the effective management and efficient integration of Distributed Energy Resources in the emerging Smart Grid. One critical component of our architecture is the Local Flexibility Estimators (LFEs) agents, which are key for offloading the Aggregator from serious or resource-intensive responsibilities--such as addressing privacy concerns and predicting the accuracy of DER statements regarding their offered demand response services.
The proposed aggregation framework allows the formation of efficient and effective LFE cooperatives. To this end, we developed and deployed a variety of cooperative member selection mechanisms, including scoring rules, and (deep) reinforcement learning. We use data from the well-known PowerTAC simulator to systematically evaluate our framework in various scenarios based on Smart Grid settings, so the efficiency of the framework can be properly assessed. Our experiments verify its effectiveness for incorporating heterogeneous DERs into the Grid in an efficient manner--showing that the use of appropriate mechanisms results in higher payments for competent LFEs managed by the Aggregator.
Professor Georgios Chalkiadakis (PhD University of Toronto, 2007) joined the faculty of the Technical University of Crete in March 2011. His research interests lie mainly in the area of Multi-Agent Systems (MAS); and more specifically on decision making under uncertainty and machine learning in MAS environments, coalition formation and cooperation in MAS, and cooperative game theory. He is a co-author of the graduate level textbook “Computational Aspects of Cooperative Game Theory” (Morgan and Claypool, 2011). He has also co-authored four chapters in scientific collections, and more than 100 research papers in journals and conferences in his areas of expertise (several of which have received awards or award nominations). He has served in the Editorial Board of the Journal of Artificial Intelligence Research; while he has served in the Boards of Directors of the Hellenic AI Society-EETN (General Secretary: 2014-2016; 2016-2018), and of the European Association for Multi-Agent Systems-EURAMAS (Deputy Chair: 2018-2020; Chair: 2020-2022). More details on Georgios and his research can be found at: http://www.intelligence.tuc.gr/~gehalk
Aula Tessari (presenza e da remoto)
Referente: Alessandro Farinelli
CSS e script comuni siti DOL - frase 9957