Unsupervised concept drift detection with a discriminative classifier
buir.contributor.author | Gözüaçık, Ömer | |
buir.contributor.author | Büyükçakır, Alican | |
buir.contributor.author | Can, Fazlı | |
dc.citation.epage | 2368 | en_US |
dc.citation.spage | 2365 | en_US |
dc.contributor.author | Gözüaçık, Ömer | en_US |
dc.contributor.author | Büyükçakır, Alican | en_US |
dc.contributor.author | Bonab, H. | en_US |
dc.contributor.author | Can, Fazlı | en_US |
dc.coverage.spatial | Beijing, China | en_US |
dc.date.accessioned | 2020-01-30T12:01:51Z | |
dc.date.available | 2020-01-30T12:01:51Z | |
dc.date.issued | 2019 | |
dc.department | Department of Electrical and Electronics Engineering | en_US |
dc.department | Department of Computer Engineering | en_US |
dc.description | Date of Conference: 3-7 November 2019 | en_US |
dc.description | Conference Name: 28th ACM International Conference on Information and Knowledge Management, CIKM 2019 | en_US |
dc.description.abstract | In data stream mining, one of the biggest challenges is to develop algorithms that deal with the changing data. As data evolve over time, static models become outdated. This phenomenon is called concept drift, and it is investigated extensively in the literature. Detecting and subsequently adapting to concept drifts yield more robust and better performing models. In this study, we present an unsupervised method called D3 which uses a discriminative classifier with a sliding window to detect concept drift by monitoring changes in the feature space. It is a simple method that can be used along with any existing classifier that does not intrinsically have a drift adaptation mechanism. We experiment on the most prevalent concept drift detectors using 8 datasets. The results demonstrate that D3 outperforms the baselines, yielding models with higher performances on both real-world and synthetic datasets. | en_US |
dc.description.provenance | Submitted by Zeynep Aykut (zeynepay@bilkent.edu.tr) on 2020-01-30T12:01:51Z No. of bitstreams: 1 Unsupervised_concept_drift_detection_with_a_discriminative_classifier.pdf: 1814205 bytes, checksum: 060996eaac7140e727a68e08bc613898 (MD5) | en |
dc.description.provenance | Made available in DSpace on 2020-01-30T12:01:51Z (GMT). No. of bitstreams: 1 Unsupervised_concept_drift_detection_with_a_discriminative_classifier.pdf: 1814205 bytes, checksum: 060996eaac7140e727a68e08bc613898 (MD5) Previous issue date: 2019 | en |
dc.description.sponsorship | ACM SIGIR | en_US |
dc.description.sponsorship | ACM SIGWEB | en_US |
dc.identifier.doi | 10.1145/3357384.3358144 | en_US |
dc.identifier.isbn | 9781450369763 | |
dc.identifier.uri | http://hdl.handle.net/11693/52934 | |
dc.language.iso | English | en_US |
dc.publisher | Association for Computing Machinery | en_US |
dc.relation.isversionof | https://dx.doi.org/10.1145/3357384.3358144 | en_US |
dc.source.title | Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM 2019 | en_US |
dc.subject | Data stream | en_US |
dc.subject | Concept drift | en_US |
dc.subject | Drift detection | en_US |
dc.title | Unsupervised concept drift detection with a discriminative classifier | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Unsupervised_concept_drift_detection_with_a_discriminative_classifier.pdf
- Size:
- 1.73 MB
- Format:
- Adobe Portable Document Format
- Description:
- View / Download
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: