Robustness Can Be Cheap: A Highly Efficient Approach to Discover Outliers under High Outlier Ratios.
Siqi WangEn ZhuXiping HuXinwang LiuQiang LiuJianping YinFei WangPublished in: AAAI (2019)
Keyphrases
- highly efficient
- outlier detection
- low cost
- detecting outliers
- detect outliers
- outlier mining
- high robustness
- low complexity
- low latency
- novelty detection
- data streams
- three dimensional
- missing data
- wide range
- sat solvers
- retrieval model
- discriminative learning
- language model
- special case
- high classification accuracy
- association rules