Challenges with Probabilistic Networks

Osmar R. Zaïane (University of Alberta, Canada)
E-mail: zaiane @
Web Page:

Much of the data in real applications can be represented as graphs where sets of vertices are joined by edges representing relationships. These are known as complex networks and much research and solutions have been proposed to such data. For some problems, nodes may even have values in networks. In the vast majority of the social network analysis solutions, the network structure is assumed to be exact and deterministically known. However, like with probabilistic databases, some applications present further complexities to information networks when the existence of some relationships is uncertain and known only with some probability, or when the values of some node attributes, or even the presence of a node is uncertain. We call these Probabilistic Complex Networks. These are gaining only few studies take the uncertainty into consideration. In this will present Probabilistic Complex Networks and the myriad still open problems they raise. We will present examples of early solutions for entity ranking, link prediction and community mining for networks with edge existential uncertainty.

Network embedding-based Geo-social Recommendation

Hongzhi Yin, The University of Queensland

Abstract: The rapid development of mobile Internet, location acquisition and 5G communication technologies has fostered a profusion of geo-social networks (e.g., Foursquare, Yelp and Google Place). They provide users an online platform to check-in at points of interests (e.g., cinemas, galleries and hotels) and share their life experiences in the physical world via mobile devices. The new dimension of location implies extensive knowledge about user behaviours and interests by bridging the gap between online social networks and the physical world. It is crucial to develop new geo-social recommendation services for both individual users and groups to explore the new places, attend new events and find their potential partners to attend these events together. This keynote will introduce three emerging geo-social recommendation paradigms and their new challenges:  spatial item recommendation for mobile users, spatial item recommendation for dynamic groups, and joint spatial item and partner recommendation.  This keynote will also explore how to adopt and advance the network embedding techniques to address the new challenges in the three geo-social recommendation services. 

Short bio: – Dr Hongzhi Yin is a senior lecturer (equivalent to Associate Professor in North America) with the University of Queensland and the winner of Australian Discovery Early Career Researcher Award (equivalent to NSF CAREER award in North America). He has been focusing on creating big commercial and social values from big user data and sensor data by developing innovative machine learning, data mining and database techniques, including deep learning, spatial-temporal data mining, probabilistic graphical model, recommender systems, social media analytics and mining, time series data mining and prediction, network embedding and mining, and smart sales and smart transportation. He has published 110+ papers and won 5 Best Paper Awards such as ICDE’19 Best Paper Award and ACM Annual Best Computing Award as the main author, and most of his research works have been published in reputed journals and top international conferences including VLDB Journal, ACM TOIS, IEEE TKDE, ACM TKDD, ACM TIST, SIGMOD, SIGKDD, PVLDB, ICDE, AAAI, IJCAI, SIGIR, WWW, ICDM, ACM Multimedia and CIKM. For more details about Dr. Hongzhi Yin, please refer to his homepage

Big Data 2.0: Future Data Computing

Guoren Wang, Beijing Institute Of Technology,China

Human beings are moving from the IT era to the DT (data technology) era in which data is the most valuable resource. In terms of Big Data computing, the mainstream computing systems of Big Data represented by Hadoop, Spark and Flink have different programming models and interfaces, which focus on batch or stream tasks respectively. With the development of mobile internet, the traditional cloud computing model has been unable to effectively promote the development of new applications such as smart homes and smart cities. Therefore, mixed batch & stream processing, cross-domain deployments and edge computing will be the development and research trends of the future big data computing.
In this talk, we will first review the traditional big data computing platforms, and introduce their development history, characteristics, advantages and core issues. We then will analyze the challenges and difficulties faced by the traditional cloud computing models from the aspects of batch & stream interactive computing, cross-data center computing and mobile edge computing. We finally propose the development and research trends for future data computing under the era of Big Data 2.0.

Bio: Guoren Wang is currently a professor at Beijing Institute of Technology, a Yangtze River scholar, a recipient of the National Science Fund for Distinguished Young Scholars, a member of the expert review team of the Information Science Department of the National Natural Science Foundation of China, and a vice chair of the Database Technical Committee of the China Computer Federation. Selected as a national candidate for the National Million Talents Project, awarded the honorary title of “Young and Middle-aged Experts with Outstanding Contributions”; Received a total of 10 provincial and ministerial science and technology awards, including the Second Prize of National Science and Technology Progress Award, the First Prize of Science and Technology Progress of Liaoning Province, the Second Prize of Natural Science of Ministry of Education, and the Second Prize of Nature Science of Liaoning Province. His doctoral students won 2 national outstanding paper nomination awards, 2 outstanding doctoral theses in Liaoning Province, and 1 excellent paper of China Computer Federation; the research field is big data management and analysis; and more than 80 papers has been published in important academic conferences and journals such as SIGMOD, VLDB, ICDE, VLDB Journal, IEEE Trans. TKDE and IEEE Trans. TPDS.

Key Dates

Important Deadlines

Full paper submission due:  26 May, 2019

Demo proposal submission due: 1 July, 2019

Acceptance notification:  1 August, 2019

Camera-ready due:  15 August, 2019

Author registration due:  30 October, 2019

Early bird registration due:  1 October, 2019

Conference time:   21-23 November, 2019

Workshop date: 24 November 2019


We invite authors to submit papers on topics of data mining and applications, including but not limited to
1. Data mining foundations;
2. Grand challenges of data mining;
3. Parallel and distributed data mining algorithms;
4. Mining on data  streams;
5. Graph mining;
6. Spatial data mining;
7. Text, video, multimedia data mining;
8. Web mining; High performance data mining algorithms;
9. Correlation mining;
10. Benchmarking and evaluations;
11. Interactive data mining;
12. Data-mining-ready structures and pre-processing;
13. Data mining visualization;
14. Information hiding in data mining;
15. Security and privacy issues;
16. Competitive analysis of mining algorithms;
17. Internet of Things mining;
18. Personalization and recommendation systems;