homarques/SIREOS

Similarity-based Unsupervised Evaluation of Outlier Detection

SIREOS (Similarity-based Internal, Relative Evaluation of Outlier Solution)

Implementation by Henrique O. Marques < oli@sdu.dk >

Repository of the paper:

H. O. Marques, A. Zimek, R. J. G. B. Campello, and J. Sander. 
Similarity-based Unsupervised Evaluation of Outlier Detection. 
In: SISAP. pp. 234-248 (2022)

Third-party indices source-codes:

• IREOS [1]
  
• EM and MV Curves [2]
  
• Laplacian Score [3]
  

Third-party datasets source-codes:

• Real-World Datasets [4]
  
• Synthetic Dataset Generator [5]
  

References

[1] Marques, H.O., Campello, R.J.G.B., Sander, J., Zimek, A.: Internal evaluation of unsupervised outlier detection. ACM Trans. Knowl. Discov. Data 14(4), 47:1–47:42 (2020)
[2] Goix, N.: How to evaluate the quality of unsupervised anomaly detection algorithms? CoRR abs/1607.01152 (2016)
[3] He, X., Cai, D., Niyogi, P.: Laplacian score for feature selection. In: NIPS. pp. 507–514 (2005)
[4] Campos, G.O., Zimek, A., Sander, J., Campello, R.J.G.B., Micenková, B., Schubert, E., Assent, I., Houle, M.E.: On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study. Data Min. Knowl. Discov. 30(4), 891–927 (2016)
[5] Iglesias, F., Zseby, T., Ferreira, D.C., Zimek, A.: MDCGen: Multidimensional dataset generator for clustering. J. Classif. 36(3), 599–618 (2019)