workshop on Mining Network Data
June 12, 2007
San Diego, CA
Sponsored by ACM SIGMETRICS
Held in conjunction with ACM SIGMETRICS '07 and FCRC '07
CALL FOR PAPERSSUBMISSION INSTRUCTIONS
Today's large scale networked systems are extensively instrumented for collecting a wealth of different types of data including traffic (e.g., packet or flow level traces), control (e.g., router forwarding tables, BGP and OSPF updates) and management (e.g., fault, SNMP traps) data. Suitable methodologies, tools and techniques are needed to process and analyze the vast amount of primarily unstructured measured data and extract structures, relationships, and "higher level knowledge" embedded in it, and use this information to aid network management and operations. The goal of this workshop is to explore new directions in and to share experiences with using data mining, and root cause analysis techniques and tools for network monitoring, management, and remediation. The workshop will provide a venue for researchers and practitioners from the networking protocols/systems, data mining, machine learning, and statistics communities, to get together and collaboratively approach this important problem of information mining for network management from their respective vantage points. Recent research efforts e.g., in anomaly detection, characterization and control are showing the potential of such an inter-disciplinary approach. The workshop solicits original / position / work-in-progress / experience papers on the application of data mining, machine learning and statistical techniques to solve network management and operation problems such as network reliability and performance, security, root-cause-analysis, troubleshooting, traffic engineering and control. This year the workshop also encourages position papers describing their research as well as practical experiences in these areas from leading researchers and industry experts. Topics of interest include, but are not limited to, the following:
- Collection, storage & access infrastructure: platform instrumentation (e.g. multi-modal, multi-resolution sensors), collection techniques (e.g. event sampling, filtering, aggregation, etc.), storage and access (e.g. retention policy, indexing techniques etc.).
- Network data analytics techniques & tools: network stream mining, network graph mining, micro-clustering, temporal and statistical correlation, causality tracking, machine learning.
- Applications to network operations & management: network problem determination, network reliability and performance, root-cause analysis, security, emerging phenomenon detection (e.g. DDoS, virus/worm, spam etc.), traffic classification.
- Experience with design and use of real systems and problem solving methodologies
Of particular interest are (i) new solution techniques as well as applications of existing techniques from data mining, machine learning and statistics to IP network problems, (ii) experiences with the use of such techniques, tools and systems, and (iii) open networking problems and challenges that would benefit from the use of such techniques.
Particularly welcomed are papers that bring out interesting and novel ideas at an early stage in their development. Selected papers will be forward-looking, with impact and implications for both operational networks and ongoing or future research.
This year we solicit two categories of paper:
Short paper/extended abstract: Expected to describe early stage work, ideas, directions that are likely to stimulate discussions. Papers should be at most 3 pages long.
Full paper: Expected to describe original and in-progress work. Papers should be at most 6 pages long.
Papers must be submitted in standard ACM format (single- spaced, double column, at least 10pt font), and in either postscript or pdf format only. Author names, affiliations, contact information, paper title and paper abstract should also be entered in ascii format at the submission website. Submit papers via the MineNet-07 submission site using EDAS.
Papers will be reviewed single blind. Accepted papers will appear in the workshop proceedings. Authors of accepted papers are expected to present their work at the workshop.
For general questions with regard to the workshop, please contact the Minenet Chairs, sen (at) research.att.com, sambits (at) us.ibm.com.
For submission site maintenance, please contact the Minenet Web Chair at: (jaideep.chandrashekar (at) intel.com, jaideepcs (at) gmail.com)
Paper Registration Deadline: 19 April 2007 at 5:00PM EDT
Paper Submission Deadline: 20 April 2007 at 11:59PM EDT
Notification Acceptance: 5 May 2007
Early Registration Deadline: May 11, 20077
Camera-ready Deadline: 21 May 200
Workshop Date: 12 June 2007