Active and semi-supervised data domain description

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Data domain description techniques aim at deriving concise descriptions of objects belonging to a category of interest. For instance, the support vector domain description (SVDD) learns a hypersphere enclosing the bulk of provided unlabeled data such that points lying outside of the ball are considered anomalous. However, relevant information such as expert and background knowledge remain unused in the unsupervised setting. In this paper, we rephrase data domain description as a semi-supervised learning task, that is, we propose a semi-supervised generalization of data domain description (SSSVDD) to process unlabeled and labeled examples. The corresponding optimization problem is non-convex. We translate it into an unconstraint, continuous problem that can be optimized accurately by gradient-based techniques. Furthermore, we devise an effective active learning strategy to query low-confidence observations. Our empirical evaluation on network intrusion detection and object recognition tasks shows that our SSSVDDs consistently outperform baseline methods in relevant learning settings.

Original languageEnglish
Title of host publicationMachine Learning and Knowledge Discovery in Databases : European Conference, ECML PKDD 2009, Bled, Slovenia, September 7-11, 2009, Proceedings, Part I
EditorsWray Buntine, Marko Grobelnik, Dunja Mladenic, John Shawe-Taylor
Number of pages16
Place of PublicationBerlin, Heidelberg
PublisherSpringer Verlag
Publication date01.07.2009
Pages407-422
ISBN (print)978-3-642-04179-2
ISBN (electronic)978-3-642-04180-8
DOIs
Publication statusPublished - 01.07.2009
Externally publishedYes
EventEuropean Conference on Machine Learning and Knowledge Discovery in Databases - 2009 - Bled, Slovenia
Duration: 07.09.200911.09.2009
https://www.k4all.org/event/european-conference-on-machine-learning-and-principles-and-practice-of-knowledge-discovery-in-databases/

    Research areas

  • Informatics - Active Learning, Background knowledge, Baseline methods, Continuous problems, Data domain description, Empirical evaluations, Gradient based, Learning settings, Network intrusion detection, Optimization problems, Semi-supervised learning, upport vector domain description, Unlabeled data
  • Business informatics

Recently viewed

Publications

  1. Spaces for challenging experiences, indeterminacy, and experimentation
  2. Efficient Order Picking Methods in Robotic Mobile Fulfillment Systems
  3. THE PARALLAX OF INDIVIDUATION
  4. Control of an Electromagnetic Linear Actuator Using Flatness Property and Systems Inversion
  5. Restricted nonlinear approximation and singular solutions of boundary integral equations
  6. Using sequential injection analysis for fast determination of phosphate in coastal waters
  7. Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration
  8. Industrial applications using wavelet packets for gross error detection
  9. Metaheuristics approach for solving personalized crew rostering problem in public bus transit
  10. On the Difficulty of Forgetting
  11. Spectral Early-Warning Signals for Sudden Changes in Time-Dependent Flow Patterns
  12. Octanol-Water Partition Coefficient Measurement by a Simple 1H NMR Method
  13. Governing Objects from a Distance
  14. Performance Saga: Interview 01
  15. A Multilevel Inverter Bridge Control Structure with Energy Storage Using Model Predictive Control for Flat Systems
  16. On the Direct Kinematics Problem of Parallel Mechanisms
  17. Pushing the Envelope: Creating Public Value in the Labor Market
  18. Making mutual learning tangible
  19. How can problems be turned into something good? The role of entrepreneurial learning and error mastery orientation
  20. Theorie des Quantum Computings
  21. Petri net based EMIS-mappers for flexible manufacturing systems
  22. Determination of 10 particle-associated multiclass polar and semi-polar pesticides from small streams using accelerated solvent extraction
  23. Performance concepts and performance theory
  24. Convergence of adaptive learning and expectational stability
  25. Introduction
  26. Analysis of the mechanical properties of an arc-sprayed WC-FeCSiMn coating
  27. Implementing the Kyoto Protocol without Russia
  28. On the role of linguistic features for comprehension and learning from STEM texts. A meta-analysis
  29. Do guided internet-based interventions result in clinically relevant changes for patients with depression?