Dr. Jeffrey Chan: Travel Itinerary Recommendation

Presenter: Jeffrey Chan

Abstract:  It is becoming increasingly popular for people to plan their own trips using online travel platforms, but they often face the dilemma of finding places they want to visit, scheduling these to maximise the time spent at interesting places (vs unnecessary travel between locations), while adhering to time and financial budgets. This is usually a time consuming, difficult and frustrating process, and often led to itineraries that are suboptimal. Hence, much research and effort has been directed at point of interest (POI) and itinerary recommendations.In this tutorial, we will introduce the problems of POI and itinerary recommendation, then go through some of the fundamental approaches to perform these types of recommendations. If time permits, we will also introduce variations of these problems.

BiographyJeffrey is currently a senior lecturer at RMIT University, Melbourne Australia. He completed his PhD at the University of Melbourne, Australia, worked at the Digital Enterprise Research Institute in Galway, Ireland and from 2015 has been at RMIT University. His work in machine learning, social network analysis, recommendation and data driven optimisation have been published in venues such as TPAMI, TKDE, DMKD, KDD, ICDM, SDM, CIKM, SIGIR, AAAI and IJCAI and has led to projects and industry collaborations in retail, transportation, non-profit, health and energy sectors. He has served on various conference organising committees, such as IJCAI, ASONAM and SDM and has won a best paper award in the ACM International Conference on Web Science in 2011.

Dr. Lina Yao: Adversarial Learning in Deep Learning based Recommender Systems

Presenter: Lina Yao

Abstract:  Deep neural networks have been demonstrating its effectiveness in recommender systems research. Recently, adversarial learning have garnered increasing interest and been leading to a surging enthusiasm for applying adversarial learning to improve recommendation performance from different aspects, including raising model robustness, alleviating data sparsity, generating initial profiles for cold-start users or items. In this talk, I will briefly introduce our recent research progress on how the adversarial learning is leveraged to alleviate multiple challenges of deep learning based recommender systems, in terms of dealing with sparse and missing data, and data noise (passive and active noise) for robustness of recommender systems.

BiographyDr. Lina Yao is currently a Scientia Associate Professor at University of New South Wales (UNSW), Australia. Her research lies in data mining and machine learning with focus on recommender systems, activity recognition, Brain Computer Interface and Internet of Things. She has published over 150 peer-reviewed papers in prestigious journals and top international conferences in the areas of data mining, machine learning and intelligent systems including ACM CACM, ACM CUSR, IEEE TMC, ACM TIST, IEEE TKDE, ACM TKDD, ACM TOIT, PR, IEEE TNSRE, IEEE TNNLS, IEEE CYB, IEEE IIT, JBHI, NeurIPS, SIGKDD, ICDM, UbiComp, AAAI, SIGIR, IJCAI and CIKM. She is serving as the Associate Editor for ACM Transactions on Sensor Networks (TOSN).