Invited Speakers

Invited Speakers

Prof.Lin Li

Wuhan University of Technology, China

Title: Hyperbolic Mutual Learning for Bundle Recommendation

Abstract: Bundle recommendation aims to accurately predict the probabilities of user interactions with bundles. Most existing effective methods learn the embeddings of users and bundles from user-bundle interaction view and user-item-bundle interaction view. However, they seldom leverage the recommendation difference caused by the distinct learning trends of two views when modeling user preferences. Meanwhile, such two view interaction graphs are typically tree-like. If the graph data with this structure is embedded in Euclidean space, it will lead to severe distortion problem. Our work is a novel Hyperbolic Mutual Learning model for Bundle Recommendation (HyperMBR). The model encodes the entities (user, item, bundle) of the two view interaction graphs in hyperbolic space to learn their accurate representations. Furthermore, a mutual distillation based on hyperbolic distance is proposed to encourage the two views to transfer knowledge for increasingly improving the recommendation performance. Extensive empirical experiments on two real-world datasets confirm that our HyperMBR achieves promising results compared to state-of-the-art bundle recommendation methods.

Experience: 

Lin Li is Professor at the School of Computer Science and Artificial Intelligence, Wuhan University of Technology. Her research interest covers Information Retrieval, Recommender Systems, Data Mining, Multimedia Computing, and Natural Language Processing. She has been a very active volunteer and leader in the intelligent informatics fields that develops algorithms and systems with real-world impact. Her research outcomes have been published in 150+ papers across many top-tier journals (e.g., TKDE, INFFUS, IPM, TOIS, TSC, etc.) and conferences (e.g., AAAI, IJCAI, WWW, CIKM, ICDM, EMNLP, ICME, ICMR, DASFAA, etc).She has held leadership positions with IEEE sponsored conferences, including Chair (or Co-chair) of program committees in BESC'19 and '20. She has also been a guest editor in top-tier journals such as WWWJ, special session chairs of ICME 2021 and ICMR 2022.

Prof.Feng Zhao

Huazhong University of Science and Technology, China

Title: IE-Evo: Internal and External Evolution-Enhanced Temporal Knowledge Graph Forecasting

Abstract: Temporal knowledge graph (TKG) forecasting is widely used in various fields due to its ability to infer future events based on historical information. Modeling the internal structures and chronological dependencies of historical subgraph sequences has been proven effective. Nevertheless, on the one hand, the TKG forecasting process generally suffers from a lack of sufficient sample data due to historical resource limitations; thus, most works focus on continuously mining the patterns of historical sequences while ignoring the semantically-rich background information provided by external knowledge, especially when historical query-related information is scarce. On the other hand, when merely serializing the given subgraph sequence to mimic its temporal evolution process, only the chronological dependencies between the subgraphs can be considered, thus ignoring the evolution of time information. Hence, a method that integrates internal and external knowledge to enhance the representations of entities is urgently needed. To this end, we propose a novel TKG forecasting method, namely, the internal and external evolution-enhanced framework (IE-Evo). For the former issue, we design an external evolution encoder and use a pre-trained language model (PLM) to provide powerful external knowledge semantics for TKG forecasting. To address the latter concern, we propose an internal evolution encoder that explicitly embeds the time information while modeling the aggregation and evolution processes of the observed sequential structural information. IE-Evo has been evaluated on four public benchmark datasets, showcasing its significant improvements across multiple evaluation metrics.

Experience: 

Professor and doctoral supervisor of School of Computer Science of Huazhong University of Science and Technology, IEEE member, ACM member, CCF member, CCF information system committee. More than 70 papers have been published (accepted) in IEEE/ACM Trans, ICDE, EMNLP, ICDM, CIKM, COLING, DASFAA and other international famous journals and top-level conferences in the field. He served as a peer reviewer for more than 30 journals, including TC, TPDS, TBD, INS, INF, ISJ, IEEE Computer, and Science in China, and served as the chairman of the procedure committee/organizing committee and member of the procedure committee of several international academic conferences. More than 20 patents have been approved/applied, and more than 10 software copyrights have been approved. Presided over a number of National Key Research and Development projects, National Natural Science Foundation of China, provincial science and technology research projects, and government/enterprise horizontal projects. He has won the Excellent Master's Thesis and Excellent Bachelor's Thesis Instructor of Hubei Province for many times, the first prize of Hubei Provincial Teaching Achievement Award and the second prize of Hubei Provincial Science and Technology Progress Award.

Prof. Xiaohui Tao

University of Southern Queensland, Australia

Title: Intelligent Data Analytics with Human-in-the-Loop for Smart Healthcare in Digital Society

Abstract: The healthcare and medical practice are now at a crossroad transforming from experience-basis to evidence-based. P4 (predictive, preventative, personalized, participatory) medicine aiming to detect and prevent disease through extensive biomarker testing, close monitoring, deep statistical analysis, and patient health coaching has been a joint endeavour by healthcare, medicine, and data science research communities, as a part of the journey towards the transformation of evidence-based medicine with human-in-the-Loop for in the digital society. In this talk, we will present and discuss our recent works in this endeavour, including several industry-connected research projects on the real-world healthcare problems, with a focus on intelligent data analytics with human-in-the-Loop. These typical works reflect our philosophy of AI research - AI by humanity, for humanity and in service to humanity.

Experience: 

Dr. Xiaohui Tao is a Full Professor at the School of Mathematics, Physics and Computing, University of Southern Queensland in Australia. His research encompasses a wide spectrum, including data analytics, machine learning, natural language processing, and health informatics. His academic contributions are well-recognized with over 180+ publications in eminent journals such as TKDE, INFFUS, IPM, and notable conferences including AAAI, IJCAI, ICDE, and CIKM. Dr. Tao's contributions to the academic community have been acknowledged with prestigious awards like the Australia Research Council Grant and the Australian Endeavour Research Fellow, as well as recognition from many international conferences. As a Senior Member of both the IEEE and ACM, Dr. Tao also contributes as the Vice Chair of the IEEE Technical Committee on Intelligent Informatics (TCII). His editorial endeavours include serving as the EiC for Natural Language Processing Journal and Editorial Board member for Information Fusion. He has further enhanced his profile by serving as PC Chair/Co-chair in conferences such as WI-IAT'23, CBD'22, BESC'21, and more. Dr. Tao concluded his PhD from the Queensland University of Technology, Australia in 2009.

Prof.Yanjie Wei

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China

Title: Efficient Analysis of Biological Big Data

Abstract: Many problems in computational life sciences rely on high-performance computing, such as protein folding, drug screening and genome assembly etc. Over the last several years, the development and training of AI models in bioinformatics also heavily depends on the computing power. In this talk, I will briefly present our research on the algorithms/tool development for efficient and accurate biological data analysis.

Experience: 

Dr. Yanjie Wei is a professor and the director of Center for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Science,  the director of Shenzhen High Performance Big Data Processing Platform. He was awarded the BHP Billiton Scientific Supervisor Award, Chinese Academy of Sciences and is an outstanding member of the Youth Promotion Association of the Chinese Academy of Sciences. He served as the chair of CBSB2018, the Program Chair of ISBRA2021 and CCF CBC2019, BoFs co-Chair at SC19. His research area focuses on high performance computing and computational biology/bioinformatics. He is the editorial member for several journal such as Future Generation Computer Systems, Interdisciplinary Sciences--Computational Life Sciences, The Innovation and Big Data Mining and Analytics. Overall he has published more than 120 peer reviewed journal/conference papers, including Nucleic Acids Research, PloS Computational Biology, Briefings in Bioinformatics, Bioinformatics, Cell Research, Proteins, J of Chemical Theory and Computation, Journal of Physical Chemistry B, ISBRA2023, BIBM2023, ICPP2016, ICPP2018, PPoPP2015.