Call for Workshop Papers

ICBK Workshop on Big Data Partitioning and Mining

Big data, as its name suggested, is referring to data of huge volume, normally at terabyte-scale or even petabyte-scale, that are generated from multi-sources, in structured/unstructured/semi-structured formats, at an overwhelming velocity that conventional models and processing techniques are failed to deal with gracefully.Since itsintroduction a decade ago, big data has attractedtremendous attention from academia and industrial players around the world, shaping the way we store, process, transfer, and utilize the huge volume ofdata generated in our daily life.To deal withvarious kind of big data, such as web data, social network data, transactional data, IoT data, spatial-temporal data, geo-tagged text data, and health care data, fundamental theories and innovative models are required so as to bridge the gap between challenges from big data and incapability of existing technologies.

The Big DataPartitioning and Mining (BDPM) workshop is a full-day event andco-located with IEEE ICBK 2017. It aims to provide a unique opportunity for researchers and practitioners working onbig data processing, data-intensive computing, and big data mining,to exchange innovative ideas and thoughts on knowledge discovery and pattern mining from big data, especially focusing onbig data mining, data partitioning, fragmented knowledgemanagement, andbig knowledge synthesizing.The scope of the workshop includes, but not limited to, the following topics 

  • Data preprocessing for web data, graph data, and big social data  

  • Probabilistic partitioning techniques for structured/unstructured/semi-structured big data

  • Graph partitioning theories and methods for big social network data

  • Pattern synthesizing for partitioned big data

  • Local pattern analysis for multi-source data

  • Online learning for bigstreaming data

  • Big knowledge management for advertising and business analysis

  • Knowledge discovery from segmented big data

  • Global knowledge approximation by analyzing local data

Organizing Committee:

Xiaofeng Zhu, University of North Carolina at Chapel Hill, USA (

Jilian Zhang, Guangxi University of Finance and Economics, China (

Shichao Zhang, Guangxi Normal University, China (

ICBK Workshop on Linked Data Mining (LDM 2017)

The Web has developed into a global information space consisting not just of linked documents, but also of Linked Data. The Linked Open Data (LOD) Cloud has gained significant traction over the past years. As of February 2017, LOD community has 1146 interlinked datasets covering diverse domains from life sciences to government data. Large-scale Linked Data has the potential to support a variety of applications ranging from open domain question answering to knowledge discovery. Thus, there has been a tremendous body of ongoing work on researches that consume Linked Data from the Web. Since Linked Data is one of the most fundamental structures to semantic web and knowledge graph, a perspective is new technologies could be developed based on Linked Data Mining (LDM).

LDM is open to covering all topics related to Linked Data publication and consumption, and especially interested in researches such as entity consolidation, association discovery, data integration, quality evaluation, search and query, and Linked Spatiotemporal Data analysis. Besides, how to achieve efficient, accurate and trustworthy mining on Linked Data has become crucial of importance that significantly impacts its future success and practical applications. LDM is looking for novel and significant research contributions addressing theoretical, analytical and empirical aspects of Linked Data together with descriptions of applied and validated industry solutions as tools, systems or architecture that benefit to Linked Data mining.

This workshop aims to bring together researchers and practitioners to discuss various aspects of LDM, and report the latest academic and industrial research results related to LDM.

Topics of interest include, but are not limited to:

  • Machine learning and data mining in Linked Data

  • Knowledge discovery in Linked data and ontologies

  • Visual analytics and visualization of Linked Data

  • Data quality, validation and data trustworthiness

  • Dynamics and evolution of LD

  • Trust, privacy, Provenance and security of Linked Data

  • Search, query and analysis in Linked Data

  • Extraction, linking and integration of LD

  • Scalability issues relating to Linked Data

  • Interoperation of Linked Spatiotemporal Data

  • Applications of Linked Data on real-world problems

Organizing Committee:

Prof. Jun Liu, Xi¡¯an Jiaotong University, China (

Prof. Zheng Yan, Aalto University, Finland / Xidian University, China (

ICBK Workshop on Research and Application of Big Knowledge in Urban Governance

Urban governance is a very complex system engineering, involving a wide range of professional fields, which interrelate and interact with each other. A large volume of data will be produced during the urban operation, but just collection and mining this data can¡¯t fully explore the real value. Based on the multi-domain data sharing, big knowledge can be used to interconnect and interoperate the acquired data and form new knowledge and new systems, acquires new knowledge, technologies and methods for urban governance so as to help solve the problem of urban operation and guarantee the safety and efficient operation of urban governance. The workshop aims to provide a platform for academic exchanges and demonstrations to exchange and discuss the current frontier research and application experience.

Topics of the workshop include, but not limited to:

  • Data mining and knowledge engineering model construction in urban governance

  • Big knowledge and urban development

  • The opportunity and challenge of big knowledge to urban governance

  • The application of big knowledge in urban planning management

  • The Influence of big knowledge in the management of smarter municipal facilities

  • How to practice the concept of "people-oriented" in urban governance

  • Management technology and method of underground pipeline operation based on big knowledge

  • How to use big knowledge to insure urban public security

  • Intelligent analysis and abnormal feature recognition of administrative data

  • Discovery of urban governance theories by big data and big knowledge

  • Research on the integration and sharing of urban municipal facilities data

  • Urban governance and efficient management based on artificial intelligence

Organizing Committee:

Kehui Liu, Beijing Institute of New Technology Application,China

Yifang Jiang, Tianjin Institute of Geotechnical Investigation Surveying,China

Huanhuan Chen, University of Science and Technology of China

ICBK Workshop on Sparse, Uncertain, and Incomplete Data Modeling and Online Learning (DMOL 2017)

The goal of the workshop is to address innovative techniques, metrics, and applications that can exploit data modeling and online learning capabilities to address the Sparse, Uncertain, and Incomplete data challenges facing real-world applications. Manuscripts are solicited to address a wide range of topics in Sparse, Uncertain, and Incomplete Data Modeling and Online Learning, but not limit to the following:

  • Data Streaming Mining

  • Feature Streaming Mining

  • Sparse Data/Knowledge Representation

  • Concept Drifting Detection on Big Data

  • Collaborative Learning on Big Data

  • Mining from Multiple Data Source

  • Uncertain Data Stream Mining

Organizing Committee:

Dr. Zhongqiu Zhao, Hefei University of Technology, China.(

Dr. Peipei Li, Hefei University of Technology, China. (

ICBK Workshop on Analyzing and Predicting Interaction Behaviors (APIB 2017)

Workshop URL£º

With the advent of Internet, it equips more and more devices (e.g., cellphone, pad and computer) with the online capability. As these devices can now meet people¡¯s various demands (e.g., working or entertaining) almost anytime and anywhere, a massive number of interaction behaviors, which containsrich information like time and actions (e.g., viewing a news or listening a song), have been recorded. It becomes possible to analyze and predict users¡¯ attitudes, preferences, personality and what people will do via this information-rich interaction behaviors, at different time-scales and at different types of interaction. Furthermore, it enables government, web holders and other service providers to improve and perfect their applications and services. During the last decade, a large body of research has been devoted on interaction behaviors analyzing and predicting. However,as interaction behaviors become extreme diverse and show a massive growth, it brings many technical and domain challenges inherent in analyzing and predicting interaction behaviors for different applications.

The goal of the workshop is to bring together researcher and practitioner from academia, and industrial to discuss and reflect various challenges and technique solutions involved in user interactive behavior analysis and prediction. We want to facilitate and promote new ideas and research on applying big scale machine learning and data mining techniques to provide more meaningful recommendation and customization experience to the end-user. The target audience will be the general researcher and practitioners in the field of machine learning, data mining and big data.

To that end, this workshop offers an opportunity to address the related research challenges and the possible solutions from both academic and industrial perspective, which includes but not limited to:

  • Normal behavior analysis (e.g., community detection)

  • Abnormal behavior analysis (e.g., churn of users)

  • Click-Through Rate (CTR) prediction

  • Expert system

  • Question-Answering (QA) system

  • Context-aware interaction behaviors mining

  • Integration of domain priors for knowledge discovery

  • Visualization, personalization, and recommendation of big knowledge navigation and interaction

Organizing Committee:

Ming Gao, East China Normal University, China (

Qi Liu, University of Science and Technology of China, China (

ICBK 2017 Workshop on Dynamic Knowledge Modeling and Evolution (DKME 2017)

Dynamic knowledge modeling and evolution (DKME) deals with the dynamic evolution of fragmented knowledge and explore its evolving mechanism, by means of computing technologies such as knowledge modeling and visualization, machine learning and big data analytics. This Workshop seeks innovative research and development that contribute to the theory and practice of dynamic knowledge modeling and evolution in big knowledge context. It intends to address the related aspects including algorithms, methodology, systems, infrastructure, evaluation and applications.

The Workshop on Dynamic Knowledge Modeling and Evolution is expected to report emerging research findings to provide an integrated view of the current state of the art, identify key challenges and opportunities for future studies, and promote the communication and exchanging of ideas among researchers and practitioners in dynamic knowledge modeling and evolution.

Areas of interest include but are not limited to the following topics:

  • Theories of the dynamic evolution of fragmented knowledge

  • Dynamic knowledge acquisition, modeling and representation in big knowledge context

  • Machine learning and pattern recognition based knowledge evolution structures mining

  • Data cleaning, interpolation and preprocessing based on evolving relations mining

  • Web-enabled big knowledge evolution systems, platforms and infrastructure

  • Evaluation, validation and visualization of DKME related algorithms, models and systems

  • Knowledge management, refinement, integration and aggregation in DKME applications

  • Emerging DKME applications and services in areas such as ebusiness, security, human machine interaction and question answering.


Contact co-organizers at

Important Dates

  • Paper submission: May 25, 2017

  • Notification of acceptance/rejection: June 5, 2017

  • Camera-Ready Papers: June 15, 2017

  • Conference: August 9-10, 2017

All deadlines are 11:59PM, UTC-12; thus submissions are allowed as long as the deadline date is not past anywhere in the world.

Submission Guidelines

Paper submissions should be no longer than 6 pages, in the IEEE 2-column format, including the bibliography and any possible appendices. Submissions longer than 6 pages will be rejected without review. All submissions will be triple-blind reviewed by the Program Committee on the basis of technical quality, relevance to Big Knowledge, originality, significance, and clarity. 

The following sections give further information for authors.  

1.      Triple blind submission guidelines

ICBK will adopt a triple blind submission and review policy for all submissions. Authors must hence not use identifying information in the text of the paper and bibliographies must be referenced to preserve anonymity. 

2.      What is triple blind reviewing?

The traditional blind paper submission hides the referee name from the authors. The triple-blind paper submission and review, in addition, also hides the authors¡¯ names from the referees, and the referees¡¯ names during review discussions. The names of authors and referees remain known only to the PC Chairs, and the author names are disclosed only after the ranking and acceptance of submissions are finalized. Although there is much debate on the merits and perceived benefits of triple blind reviewing, these are not discussed here. Our main purpose is to implement this policy in ICBK toward understanding the influence of the authors¡¯ identity, whether conscious or unconscious, on the reviewer¡¯s attitude toward a submission. Hence it is imperative that all authors of ICBK submissions work on concealing their identity in the content of the paper. It does not suffice to simply remove the authors¡¯ names from the first page.

3.      How to prepare your submissions

  • The authors shall omit their names from the submission. For formatting templates with author and institution information, simply replace all these information in the template by ¡°Anonymous¡±.

  • In the submission, the authors¡¯ should refer to their own prior work like the prior work of any other author, and include all relevant citations. This can be done either by referring to their prior work in the third person or referencing      papers generically. For example, if your name is Jack and you have worked on classification, instead of saying ¡°We extend our earlier classification model (Gordan 2010),¡± you may say ¡°We extend Gordan¡¯s (Gordan 2010) earlier classification model.¡±

  • The authors shall exclude citations to their own work which is not fundamental to understanding the paper, including prior versions (e.g., technical reports, unpublished internal documents) of the submitted paper. They should reference only necessary work using point (2). Hence, do not write: ¡°In our previous work [5]¡± as it reveals that citation 5 is written by the current authors.

  • The authors shall remove mention of funding sources, personal acknowledgments, and other such auxiliary information that could be related to their identities. These can be reinstituted in the camera-ready copy once the paper is accepted for publication.

  • The authors shall make statements on well-known or unique systems that identify an author, as vague in respect to identifying the authors as possible.

  • The submitted files shall be named with care to ensure that authors¡¯ anonymity is not compromised by the file name. E.g., do not name your submission ¡°.pdf¡±, instead give it a name that is descriptive of the title of your paper, such as ¡°NewApproachForClassfication.pdf¡± (or a shorter version of the same).

All manuscripts are submitted as full papers and are reviewed based on their scientific merit. The reviewing process is confidential. There is no separate abstract submission step. Manuscripts must be submitted electronically in 

We do not accept email submissions.