Tutorial Talks


  1. Title : AI Models and Trust
    • Authors
      Himanshu Gupta, IBM Research, India
      Diptikalyan Saha, IBM Research, India
      Vijay Arya, IBM Research, India

    • Abstract
      In this tutorial, we will discuss - how we can trust AI models? Put simply, we trust things which behave as we expect them to. We will discuss four key requirements - bias, lineage, explainability and robustness, which go a long way towards trusting an AI model and understanding their behavior. We will discuss few AI trust and governance use-cases and how these use-cases inter-relate with bias, explainability, lineage and robustness requirements. We will provide a brief overview of the research efforts in these four domains and outline some research problems in this space. At IBM, we have been working on building a trusted AI platform and we will also discuss some insights from our experience.

    • Biography

      Himanshu Gupta is a senior researcher at AI Engineering department of IBM Research - India. He received his MS and BTech in Computer Science from IIT Delhi and IIT Kanpur respectively. His research interests include data management, data mining, information integration, Spark/map-reduce based processing etc. His current focus in on building scalable lineage services on IBM watson data platform.

      Diptikalyan Saha is a senior researcher and manager in AI Engineering department of IBM Research - India. He received his Ph.D. degree in Computer Science from the State University of New York at Stony Brook and his BE from Jadavpur university. His research interests include Artificial Intelligence, NLP, Knowledge representation, Program Analysis, Security, Software Debugging, Testing, Verification, and Programming Languages. His current focus is on building dependable AI systems using bias and adversarial testing, debugging, and verification.

      Vijay Arya is a senior researcher at AI Engineering department of IBM Research - India. He received his Ph.D. degree in Computer Science from INRIA, France. His research interests include security, machine learning and data management. His current focus is on developing explainable ML models.


  2. Title : Post facto of Cambridge Analytica- The Dawn of Social Computing
    • Authors
      Amitava Das, Mahindra Ecole Centrale, Hyderabad, India
      Tanmoy Chakraborty, IIIT Delhi, India

    • Abstract
      The unexpected win of Trump at least has proven one fact that social computing --- personality, values, ethnicity, gender, political view analysis from social media content have immense power and it can change the shape of the world! Facebook and the data analytics company called Cambridge Analytica are at the center of a dispute over the harvesting and use of personal data. The question comes - what to learn from the history? Social Science is on the verge of a paradigm shift that allows us to ask and answer questions that were unthinkable a few decades ago. We can now collect data about human behavior on a scale never before possible and with tremendous granularity and precision, but as always said - great power comes with great responsibility.
      Therefore, Social Computing has been emerging as an independent research problem. Social Computing, mostly deals with a data-driven understanding of complex social networks, which often requires knowledge about graph analysis, data mining, natural language processing, and machine learning. Therefore, this tutorial is formed around five major topics that all fall under the emerging field of computational social science: Psychology and Sociology, Natural Language Processing, Complex Network, Big Data, and Machine Learning and how to use them together to answer few buzzing questions of our times.

    • Biography

      Amitava Das is an Associate Professor in the department of Computer Science & Engineering at Mahindra Ecole Centrale, Hyderabad. Earlier he worked for IIIT Sri City. In his research career he has spent significant time in USA, Europe and Japan and also worked for Samsung Research India. His research area is sentiment analysis, NLP, Social Computing, conversational AI, and Deep Learning. Currently he is consulting for AI-NLP with several Indian IT companies including Wipro.

      Tanmoy Chakraborty is an Assistant Professor and a Ramanujan Fellow at the Dept. of Computer Science & Engg., IIIT Delhi, India. Prior to this, he was a postdoctoral researcher in University of Maryland, College Park, USA. He completed his Ph.D as a Google India PhD fellow at IIT Kharagpur, India in 2015. His primary research interests include social network analysis, Data Mining, and Natural Language Processing. He has received several awards including the Google India Faculty Award, Early Career Research Award, DAAD Faculty fellowship, Best reviewer award in WWW'18, best PhD thesis award by Xerox Research, IBM Research and Indian National Academy of Engineering (INAE). He has been serving as a PC member of several conferences including WWW, WSDM, NAACL, AAAI, IJCAI, PAKDD.


  3. Title : Spatial Co-location Pattern Mining
    • Authors
      Venkata M. Viswanath Gunturi, IIT, Ropar, Punjab, India

    • Abstract
      Widespread use of spatial computing technologies has lead to increasing interest in mining interesting and non-trivial patterns from spatial data. Over the years several works have made progress towards this end by exploring different aspects of the problem of finding patterns from data which is embedded in a geographic space. This talk would focus on one particular pattern family called the spatial co-location patterns which have gained widespread attention due to their potential uses. The talk would cover well known algorithms for mining spatial co-location patterns from large dataset in a time-efficient manner. We would also cover some of the new directions of research being explored in this area.

    • Biography
      Dr. Venkata Gunturi is an Assistant Professor at the Indian Institute of Technology Ropar. He obtained his PhD from the Dept of Computer Science and Engineering at the University of Minnesota, Minneapolis, USA. His research interests include spatial and spatio-temporal databases, spatial data mining, navigation algorithms on spatial networks. He is a recipient of the Early Career Award from DST, SERB

  4. Title : Emerging Technologies and Opportunities for Financial
               Data Analytics: A perspective
    • Authors
      Anirban Mondal, Ashoka University, Sonipat, Haryana, India
      Atul Singh, Fidelity Management and Research, Bengaluru, India

    • Abstract
      Several key transformations in the macro-environment coupled with recent advances in technology have opened up tremendous opportunities for innovation in the financial services industry. We discuss the implications and ramifications of these macro-environmental trends for data science research. Moreover, we describe novel and innovative IT-enabled applications, use-cases and techniques in retail financial services as well as in financial investment services. Furthermore, this tutorial identifies the research challenges that need to be addressed for realizing the full potential of innovation in financial services. Examples of such research challenges include context-aware analytics over uncertain and imprecise data, data reasoning and semantics, cognitive and behavioural analytics, design of user-friendly interfaces for improved expressiveness in querying financial service providers, personalization based on fine-grained user preferences and financial Big Data processing on Cloud- based infrastructure. Additionally, we discuss new and exciting opportunities for innovation in financial services by leveraging the new and emerging financial technologies as well as Big Data technologies.

    • Biography

      Anirban Mondal is an Associate Professor of Computer Science at Ashoka University. His broad research interest is in big data analytics, urban informatics, financial analytics, mobile crowdsourcing, large-scale distributed systems and database indexing. He has an established reputation, key presence and high visibility in the international research community. He has numerous publications in key conferences/journals and has also been actively involved as a PC Chair/Co-chair, PC member, journal reviewer as well as keynote/tutorial speaker at reputed international conferences/workshops. He has served as an ACM India Eminent Speaker and has also been awarded the prestigious JSPS (Japanese Society for Promotion of Sciences) Fellowship. He has research collaborations with prestigious Universities in Japan, Singapore, USA, Australia and India. Prior to this, he has worked in organizations such as University of Tokyo, Xerox Research Lab and IIIT Delhi. Based on his industry experience in designing practical research applications in urban informatics and financial analytics, he has multiple USPTO granted patents as well as several filed patents. He holds a PhD in Computer Science from the National University of Singapore, an MBA from the University of Massachusetts Amherst (UMass) and a BTech from the Indian Institute of Technology (IIT) Kharagpur. His technological expertise coupled with his business capabilities as well as his ability to create a big vision and execute it to completion in diverse multi-cultural settings make him an exciting innovator.

      Atul Singh is a data scientist at a reputed financial firm. His research interests include Natural Language Processing (NLP), geo-spatial analytics and reinforcement learning with a focus on finance. He has over sixteen years of software industry work experience in research, and innovation. Prior to his current employment, he has worked at Xerox Research Centre India and Robert Bosch Research Technology Centre India. He has nine granted US patents, eleven pending US patent applications, and several research publications in various international forums. He has given several seminars in the field of financial data analytics and big data. He has a PhD in Computer Science from Trinity College Ireland, and a B.Tech from Indian Institute of Technology Kanpur.


  5. Title: Malware Detection using Machine Learning and Deep Learning
    • Authors
      Hemant Rathore, BITS, Pilani, Goa Campus, India
      Swati Agarwal, BITS, Pilani, Goa Campus, India
      Sanjay K. Sahay, BITS, Pilani, Goa Campus, India
      Mohit Sewak, BITS, Pilani, Goa Campus, India

    • Abstract
      Research shows that over the last decade, malware have been growing exponentially, causing substantial financial losses to various organizations. Different anti-malware companies have been proposing solutions to defend attacks from these malware. The velocity, volume, and the complexity of malware are posing new challenges to the anti-malware community. Current state-of-the-art research shows that recently, researchers and anti-virus organizations started applying machine learning and deep learning methods for malware analysis and detection. We have used opcode frequency as a feature vector and applied unsupervised learning in addition to supervised learning for malware classification. The focus of this tutorial is to present our work on detecting malware with (1) various machine learning algorithms and (2) deep learning models. Our results show that the Random Forest outperforms Deep Neural Network with opcode frequency as a feature. Also in feature reduction, Deep Auto-Encoders are overkill for the dataset, and elementary function like Variance Threshold perform better than others. In addition to the proposed methodologies, we will also discuss the additional issues and the unique challenges in the domain, open research problems, limitations, and future directions.

    • Biography

      Hemant Rathore is an Assistant Professor Department of CS and IS at BITS, Pilani, Goa Campus, India. He is currently pursuing his PhD in Malware Analysis and Detection. He graduated with an M.E. degree from BITS Pilani in 2013. He worked in the area of Computer Security for 3 years at Symantec, India. His research interests are in the area of Data Mining, Malware Analysis, Network Security, Cryptography, Machine Learning, and Operating Systems.

      Swati Agarwal is a Visiting Assistant Professor in Computer Science Department at BITS Pilani-Goa, India. Her research interests are in the area of Social Computing, Natural Language Processing, Security Informatics, and Text mining and Analytics. She has a PhD in Computer Science (Social Media Analytics and Security Informatics) from IIIT-Delhi in 2017. She has been serving as a TPC member of various conferences and workshops including PAKDD, ADMA, NAACL, ACL, COLING and many more.

      Sanjay K. Sahay is an Associate Professor in the Department of CS and IS at BITS Pilani, Goa Campus, India. He is also a Visiting Associate of IUCAA, Pune. His research interests are in the area of Network Security, Information Security, Data Science, and Gravitational Waves. Under his supervision three PhD has been graduated, one has submitted the PhD thesis and currently supervising two students.

      Mohit Sewak is a senior Research Scholar at BITS Pilani, Goa Campus. He has 14 years of rich Industry experience in the space of Machine Learning and Cognitive Computing. Mohit has so far authored two books, and he has been the lead/solo inventor of 12+ patents 4 (Granted) and 8+ (Applied) with the USPTO.


The Sixth International Conference On
Big Data Analytics
December 18 - 21, 2018

Organizing Institute

Publication


Partner Institutions/Organizations