Heuristic sample reduction method for support vector data description

Sun, Weidong; Qu, Jian; Chen, Yang; Di, Yazhou; Gao, Feng

doi:10.3906/elk-1307-137

Cited by 10 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…b) Pruning: The idea of pruning is to iteratively remove observations from high-density regions as long as the sample remains "density-connected". One way to achieve this is by pruning all neighbors of an observation closer than a minimum distance, starting from the observation closest to the cluster mean [13]. Yet this approach requires to set the minimum distance threshold, and a good choice is data dependent.…”

Section: B Sampling Methodsmentioning

confidence: 99%

“…Reduction Sampling [9][10][11][12][13][14][15][16][17][18] Kernel Matrix [24][25][26][27][28][29] Optimization [5][6][7][8] Fast Inference [2,[30][31][32][33] post-processing pre-processing efficient if the number of support vectors is low. Also note that under mild assumptions, SVDD is equivalent to ν-SVM [20].…”

Section: Fast Trainingmentioning

confidence: 99%

“…For Reduction, one can distinguish further: A first type reduces the number of observations by Sampling. This is the category of methods mentioned in our introduction [9][10][11][12][13][14][15][16][17][18]. A second type reduces the size of the Kernel matrix, e.g., by approximation [24][25][26][27].…”

Section: A Categorizationmentioning

confidence: 99%

“…Even efficient solvers like decomposition methods [5][6][7][8] result in training times prohibitive for many applications. In these cases, sampling for data reduction is essential [9][10][11][12][13][14][15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Efficient SVDD Sampling with Approximation Guarantees for the Decision Boundary

Englhardt¹,

Trittenbach²,

Kottke³

et al. 2020

Preprint

View full text Add to dashboard Cite

Support Vector Data Description (SVDD) is a popular one-class classifiers for anomaly and novelty detection. But despite its effectiveness, SVDD does not scale well with data size. To avoid prohibitive training times, sampling methods select small subsets of the training data on which SVDD trains a decision boundary hopefully equivalent to the one obtained on the full data set. According to the literature, a good sample should therefore contain so-called boundary observations that SVDD would select as support vectors on the full data set. However, non-boundary observations also are essential to not fragment contiguous inlier regions and avoid poor classification accuracy. Other aspects, such as selecting a sufficiently representative sample, are important as well. But existing sampling methods largely overlook them, resulting in poor classification accuracy.In this article, we study how to select a sample considering these points. Our approach is to frame SVDD sampling as an optimization problem, where constraints guarantee that sampling indeed approximates the original decision boundary. We then propose RAPID, an efficient algorithm to solve this optimization problem. RAPID does not require any tuning of parameters, is easy to implement and scales well to large data sets. We evaluate our approach on real-world and synthetic data. Our evaluation is the most comprehensive one for SVDD sampling so far. Our results show that RAPID outperforms its competitors in classification accuracy, in sample size, and in runtime.

show abstract

Section: B Sampling Methodsmentioning

confidence: 99%

Section: Fast Trainingmentioning

confidence: 99%

Section: A Categorizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient SVDD Sampling with Approximation Guarantees for the Decision Boundary

Englhardt¹,

Trittenbach²,

Kottke³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

Efficient SVDD sampling with approximation guarantees for the decision boundary

et al. 2022

View full text Add to dashboard Cite

Support Vector Data Description (SVDD) is a popular one-class classifier for anomaly and novelty detection. But despite its effectiveness, SVDD does not scale well with data size. To avoid prohibitive training times, sampling methods select small subsets of the training data on which SVDD trains a decision boundary hopefully equivalent to the one obtained on the full data set. According to the literature, a good sample should therefore contain so-called boundary observations that SVDD would select as support vectors on the full data set. However, non-boundary observations also are essential to not fragment contiguous inlier regions and avoid poor classification accuracy. Other aspects, such as selecting a sufficiently representative sample, are important as well. But existing sampling methods largely overlook them, resulting in poor classification accuracy. In this article, we study how to select a sample considering these points. Our approach is to frame SVDD sampling as an optimization problem, where constraints guarantee that sampling indeed approximates the original decision boundary. We then propose RAPID, an efficient algorithm to solve this optimization problem. RAPID does not require any tuning of parameters, is easy to implement and scales well to large data sets. We evaluate our approach on real-world and synthetic data. Our evaluation is the most comprehensive one for SVDD sampling so far. Our results show that RAPID outperforms its competitors in classification accuracy, in sample size, and in runtime.

show abstract