PRIMORIS      Contacts      FAQs      INSTICC Portal
 

Keynote Lectures

Not ACID, not BASE, but SALT: A Transaction Processing Perspective on Blockchains
Stefan Tai, TU Berlin, Germany

Privacy-preserving Machine Learning over Sensitive Data
Jin Li, Guangzhou University, China

Big Data, Smart Data and Imbalanced Classification: Preprocessing, Models and Challenges
Francisco Herrera, University of Granada, Spain

 

Not ACID, not BASE, but SALT: A Transaction Processing Perspective on Blockchains

Stefan Tai
TU Berlin
Germany
 

Brief Bio
Stefan Tai is Full Professor and Head of Chair Information Systems Engineering at TU Berlin, Germany (2014-present). Prior to that, he was a Full Professor at the Karlsruhe Institute of Technology, Germany (2007-2014) and a Research Staff Member at the IBM Thomas J. Watson Research Center in New York, USA (1999-2007). Overall, Stefan has over 20 years of experience in cutting-edge IT research and development in both academia and in industry. Stefan works on creating next-generation IT software systems that provide a necessary foundation to address larger societal challenges. His research interests include distributed information systems, cloud services and systems, and the Web as a platform for technology, social, and business innovation. Currently, Stefan works passionately on blockchain-based solutions for a diversity of application domains. Stefan was involved in a number of industrial developments (mostly with IBM), holds several patents in the area of enterprise middleware and distributed systems, and has published over 100 peer-reviewed research articles. A new book on “Cloud Service Benchmarking” will appear in 2017, to be published by Springer. Stefan serves regularly as PC member of key conferences, as member of four editorial boards of relevant journals in the field, and as expert evaluator for scientific programs worldwide. He also acts as advisor to global IT companies and as mentor to start-up companies.


Abstract
Traditional ACID transactions, typically supported by relational database management systems, emphasize database consistency. BASE provides a model that trades some consistency for availability, and is typically favored by cloud systems and NoSQL data stores. With the increasing popularity of blockchain technology, another alternative to both ACID and BASE is introduced: SALT. Compromising scalability (for now), emphasis is set on symmetric, admin-free (but outcome-agreed), ledgered, and tamper-proof decentralized transaction processing. In this keynote, we discuss these three alternatives and describe current research activities and directions for building decentralized applications using blockchains.



 

 

Privacy-preserving Machine Learning over Sensitive Data

Jin Li
Guangzhou University
China
 

Brief Bio
Jin Li is a professor at Guangzhou University. His research interests include design of secure protocols in Cloud Computing, cryptography, and machine learning. He served as a senior research associate at Korea Advanced Institute of Technology (Korea), VirginiaTech (U.S.A.), and Illinois Institute of Technology. He has published more than 100 papers in international conferences and journals, including IEEE INFOCOM, IEEE Transaction on Parallel and Distributed Computation, IEEE Transactions on Computers, IEEE Transactions on Cloud Computing and ESORICS etc. His work has been cited more than 5000 times at Google Scholar and the H-Index is 28.
He also served as program chairs and committee for many international conferences such as CSE 2017, ISICA 2015, 3PGCIC20 14, ICCCN and CloudCom etc. He received two National Science Foundation of China (NSFC) Grants for his research on Security and Privacy in Cloud Computing. He is also panel of NSFC He is PI for more than 15 funding. He has been selected as one of science and technology new stars in Guangzhou and outstanding young scholar in Guangdong province.


Abstract
Machine learning has been applied widely for classifying and recognizing complex data. However, security and privacy issues arise when the data are sensitive or the computing and data storage services are outsourced in the cloud computing. When the data are sensitive and the data evaluators are not fully trusted, the data have to be encrypted and traditional methods cannot be utilized to process the data. In this talk, I will introduce some basic solutions and challenges in this topic. Finally, I will show our method to solve this problem.



 

 

Big Data, Smart Data and Imbalanced Classification: Preprocessing, Models and Challenges

Francisco Herrera
University of Granada
Spain
 

Brief Bio
Francisco Herrera (SM'15) received his M.Sc. in Mathematics in 1988 and Ph.D. in Mathematics in 1991, both from the University of Granada, Spain. He is currently a Professor in the Department of Computer Science and Artificial Intelligence at the University of Granada. He has been the supervisor of 40 Ph.D. students. He has published more than 300 journal papers that have received more than 50000 citations (Scholar Google, H-index 112). He is coauthor of the books "Genetic Fuzzy Systems" (World Scientific, 2001) and "Data Preprocessing in Data Mining" (Springer, 2015), "The 2-tuple Linguistic Model. Computing with Words in Decision Making" (Springer, 2015), "Multilabel Classification. Problem analysis, metrics and techniques" (Springer, 2016), "Multiple Instance Learning. Foundations and Algorithms" (Springer, 2016). He currently acts as Editor in Chief of the international journals "Information Fusion" (Elsevier) and “Progress in Artificial Intelligence (Springer). He acts as editorial member of a dozen of journals. He received several honors and awards: ECCAI Fellow 2009, IFSA Fellow 2013, 2010 Spanish National Award on Computer Science ARITMEL to the "Spanish Engineer on Computer Science", International Cajastur "Mamdani" Prize for Soft Computing (Fourth Edition, 2010), IEEE Transactions on Fuzzy System Outstanding 2008 and 2012 Paper Award (bestowed in 2011 and 2015 respectively), 2011 Lotfi A. Zadeh Prize Best paper Award of the International Fuzzy Systems Association, 2013 AEPIA Award to a scientific career in Artificial Intelligence, and 2014 XV Andalucía Research Prize Maimónides (by the regional government of Andalucía). He has been selected as a 2014 Thomson Reuters Highly Cited Researcher http://highlycited.com/ (in the fields of Computer Science and Engineering, respectively) .


Abstract
Big Data applications are emerging during the last years, and researchers from many disciplines are aware of the high advantages related to the knowledge extraction from this type of problem. To overcome this issue, the MapReduce framework has arisen as a"de facto" solution. Basically, it carries out a "divide-and-conquer" distributed procedure in a fault-tolerant way to adapt for commodity hardware. Learning with imbalanced data refers to the scenario in which the amounts of instances that represent the concepts in a given problem follow a different distribution. The main issue when addressing such a learning problem is when the accuracy achieved for each class is also different. This situation occurs since the learning process of most classification algorithm is often biased towards the majority class examples, so that minorities ones are not well modeled into the final system. Being a very common scenario in real life applications, the interest of researchers and practitioners on the topic has grown significantly during these years. Being still a recent discipline, few research has been conducted on imbalanced classification for Big Data. The reasons behind this are mainly the difficulties in adapting standard techniques to the MapReduce programming style. Additionally, inner problems of imbalanced data, namely lack of data and small disjuncts are accentuated during the data partitioning to fit the MapReduce programming style.
In this talk we will pay attention to the imbalanced big data classification problem, we will analyze the current research state of this are, the behavior of standard preprocessing techniques in this particular framework toward, and we will carry out a discussion on the challenges and future directions for the topic.



footer