Scaling out Big Data Missing Value Imputations: Pythia vs. Godzilla
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-04241
- Type
- E - Conference contribution
- DOI
-
10.1145/2623330.2623615
- Title of conference / published proceedings
- 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '14)
- First page
- 651
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- August
- Year of publication
- 2014
- URL
-
http://eprints.gla.ac.uk/109764/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: The paper proposes a novel statistical learning methodology for decentralized missing value imputation tasks in Big Data systems. SIGNIFICANCE: This work was published at the top-ranked conference on Knowledge Discovery and Data Mining and won an award by the Editor-in-Chief, Journal of Big Data. It summarizes the achievements of EU/ESF and NSRF/Thalis-funded projects into Data Mining systems. RIGOUR: The work provides a comprehensive and rigorous analytical formulation, with convergence proofs of distributed machine learning algorithms for scaling out missing value imputations tasks, evaluated using a combination of simulation and testbed experiments in commercial Big Data systems.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -