Tackling heterogeneous concept drift with the Self-Adjusting Memory (SAM)

@article{Losing2017TacklingHC,
  title={Tackling heterogeneous concept drift with the Self-Adjusting Memory (SAM)},
  author={Viktor Losing and B. Hammer and H. Wersing},
  journal={Knowledge and Information Systems},
  year={2017},
  volume={54},
  pages={171-201}
}
Data mining in non-stationary data streams is particularly relevant in the context of Internet of Things and Big Data. Its challenges arise from fundamentally different drift types violating assumptions of data independence or stationarity. Available methods often struggle with certain forms of drift or require unavailable a priori task knowledge. We propose the Self-Adjusting Memory (SAM) model for the k-nearest-neighbor (kNN) algorithm. SAM-kNN can deal with heterogeneous concept drift, i.e… Expand
21 Citations
Self-Adjusting Memory: How to Deal with Diverse Drift Types
  • 9
  • PDF
Multi-label kNN Classifier with Self Adjusting Memory for Drifting Data Streams
  • 7
  • Highly Influenced
  • PDF
Multi-Label Punitive kNN with Self-Adjusting Memory for Drifting Data Streams
  • 6
  • Highly Influenced
Mitigating Concept Drift via Rejection
  • 7
  • PDF
Counterfactual Explanations of Concept Drift
  • 1
  • PDF
Statistical Mechanics of On-Line Learning Under Concept Drift
  • 11
  • PDF
Analysis of Drifting Features
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 52 REFERENCES
Learning in the presence of concept drift and hidden contexts
  • 582
  • PDF
Efficient data stream classification via probabilistic adaptive windows
  • 60
  • Highly Influential
  • PDF
Incremental Learning of Concept Drift in Nonstationary Environments
  • 587
  • Highly Influential
  • PDF
Learning from Time-Changing Data with Adaptive Windowing
  • 858
  • Highly Influential
  • PDF
A survey on concept drift adaptation
  • 1,458
  • PDF
Detecting Concept Drift with Support Vector Machines
  • 472
  • PDF
Online Learning: Searching for the Best Forgetting Strategy under Concept Drift
  • 12
  • PDF
Enabling Fast Lazy Learning for Data Streams
  • 40
  • PDF
...
1
2
3
4
5
...