NDA 2017 - 2nd International Workshop on Network Data Analytics 2017

2nd International Workshop on Network Data Analytics 2017
Co-located with the ACM SIGMOD'17
May 19 2017, Raleigh, North Carolina, USA
Workshop Website: https://sites.google.com/site/networkdataanalytics...
Proceedings will be published by ACM
WORKSHOP
The Second International Workshop on Network Data Analytics (NDA 2017), co-located with the ACM SIGMOD Conference 2017, is a forum for exchanging ideas and methods for mining, querying and learning with (large-scale) real-world networks, developing new common understandings of the problems at hand, sharing of data sets where applicable, and leveraging existing knowledge from different disciplines. This year, we have a special focus on (1) research work pertaining to presence of noise in real-life graphs and (2) novel applications of graph analytics in newer domains (like transportation, education, retail/marketing, banking, healthcare etc.) (preferably with demonstrations).
TOPICS OF INTEREST
Topics of interest include but not limited to the following:
- Core Graph Platform work which build on new age systems like Titan, SPARK/GraphX, GraphLab/PowerGraph, Giraph, GraphChi etc.
- Network representation, storage, indexing and querying methods
- Graph query languages, visualization techniques and querying interfaces
- Benchmarking RDF/SPARQL, Titan/Gremlin and/or graph database systems
- Dynamic Graphs: Managing network updates; Analysing evolution and detection of community structures in real-world graphs
- Querying and mining heterogeneous networks -- knowledge graphs etc.
- Graph summarization and sampling
- Machine learning techniques such as clustering, classification, semi-supervised learning, spectral techniques, and kernel methods in the context of networks
- Frequent/Significant sub-graph mining, graph (sub)pattern matching
- Parallel graph processing techniques/architectures
- Game Theory, Social contagion and Information propagation with applications in real-world networks:
* Rumour proliferation
* E-reputation; Viral Marketing
* Disease propagation
* Modelling traffic flow/spread
- Measuring graph characteristics?diameter, eigenvalues, triangle counting
- Noisy Graph Analytics:
* Characterization and quantification of noise in real-life graphs
* Benchmarking state-of-the-art algorithms on noisy graphs
* Graph Noise Removal: Identification, reconstruction and cleaning
- Spatio-temporal analytics:
* Streaming sensor data
* Trajectory data
* Time varying graphs -- road-networks, characterizing traffic data, co-purchase networks, biological networks -- protein-protein and * gene interaction networks etc.
- Novel Applications/Real-life experiences in Interesting Domains:
* Social Networks; Citation Networks; Co-Purchase Networks
* Biological Network Data; Ecological data
* Retail, Marketing and Media
* Financial Services and Business Data Analysis
* Customer Care; Healthcare; Transportation data Cybersecurity
MOTIVATION
Networks are prevalent in today’s electronic world in a wide variety of domains ranging from Engineering to Social Sciences, Life Sciences to Physical Sciences, Data Analytics and so on. Researchers and practitioners have studied networks in multiple ways like defining network metrics, providing theoretical results and examining problems like pattern mining, link prediction etc. Recently, we have witnessed a proliferation of networks in new business domains like Telecommunications, Banking, Retail/Marketing, Healthcare, Transportation etc. Most of these real-world applications give rise to networks which exhibit unique and interesting structures supporting multiple dynamical processes that shape these networks over time.
Graphs are unarguably one of the most natural ways of representation for such data because of their ability to represent different entity and relationship types, including the temporal relationships necessary to represent the dynamics of a data stream. However, fusing such heterogeneous data into a single graph or multiple related graphs and mining is challenging task. Emerging massive data has made calls for fundamental change to graph data modelling and programming paradigm. APACHE SPARK is one such successful instantiation. Finally, it is interesting to see the applicability of graph based techniques by applying them to even wider range of data like spatial, spatio-temporal and IOT data which did not inherently exhibit network structure by modelling relationships.
IMPORTANT DATES
Abstract Submission :January 9, 2017
Paper Submission : January 16, 2017
Notifications : March 6, 2017
Camera Ready Submission : March 27, 2017
Workshop Date : May 19, 2017
All deadlines are 23:59 Hours PST
SUBMISSION GUIDELINES
Research papers submitted to NDA should present unpublished research papers (full and short), demonstrations and case-studies in the broad area of network/graph analytics as listed above. Submissions must follow the 2 column SIGMOD Proceedings Format, and should be double-blind. For templates and details, please visit https://sites.google.com/site/networkdataanalytics....
The workshop proceedings will be published by ACM.
SUBMISSION SITE
https://cmt3.research.microsoft.com/NDA2017
Keynote Speaker
Prof. Jiawei Han has kindly agreed to deliver an exciting keynote at the workshop. The details will be posted later on the website.