A multi-level knee point based multi-objective evolutionary algorithm for AUC maximization
- 2 Downloads
The area under receiver operating characteristic curve (AUC) is one of the widely used metrics for measuring imbalanced data classification results. Designing multi-objective evolutionary algorithms for AUC maximization problem has attracted much attention of researchers recently. However, most of these methods either search the Pareto front directly, or perform tailored convex hull search for AUC maximization. None of them take the advantage of multi-level knee points found in the process of evolution for AUC maximization. To this end, this paper proposes a multi-level knee point based multi-objective evolutionary algorithm (named MKnEA-AUC) for AUC maximization on the basis of a recently developed knee point driven evolutionary algorithm for multi/many-objective optimization. In MKnEA-AUC, an adaptive clustering strategy is proposed for automatically determining the knee points on the current population. By utilizing the preference of found knee points, the evolution of the population can converge quickly. We verify the effectiveness of the proposed algorithm MKnEA-AUC on 13 widely used benchmark data sets and the experimental results demonstrate that MKnEA-AUC is superior over the state-of-the-art algorithms for AUC maximization.
KeywordsAUC maximization Multi-objective evolutionary algorithm Knee points Adaptive clustering strategy
This work is supported by National Nature Science Foundation of China (Grant Nos. 61502001, 61502004), Scientific Research Startup Fund for Doctors of Anhui University, by the Academic and Technology Leader Imported Project of Anhui University (No. J01006057). This work was also supported in part by the Natural Science Foundation of Anhui Province (Grant No. 1708085MF166), Humanities and Social Sciences Project of Chinese Ministry of Education (Grant No. 18YJC870004) and Key Program of Natural Science Project of Educational Commission of Anhui Province (Grant No. KJ2017A013).
- 2.Welleck SJ (2016) Efficient AUC optimization for information ranking applications. In: European conference on information retrieval, pp 159–170Google Scholar
- 4.Matey JR, Quinn GW, Grother P, Tabassi E, Watson C, Wayman JL (2015) Modest proposals for improving biometric recognition papers. In: IEEE International conference on biometrics theory, applications and systems, pp 1–7Google Scholar
- 11.Gräning L, Jin Y, Sendhoff B (2006) Generalization improvement in multi-objective learning. In: International joint conference on neural networks, pp 4839–4846Google Scholar
- 15.Cococcioni M, Ducange P, Lazzerini B, Marcelloni F (2007) A new multi-objective evolutionary algorithm based on convex hull for binary classifier optimization. In: IEEE congress on evolutionary computation, pp 3150–3156Google Scholar
- 16.Wang P, Emmerich M, Li R, Tang K, Baeck T, Yao X (2013) Convex hull-based multi-objective genetic programming for maximizing ROC performance. Neurocomputing 125(3):102–118Google Scholar
- 22.Li M, Zheng J (2009) Spread assessment for evolutionary multi-objective optimization. In: International conference on evolutionary multi-criterion optimization, pp 216–230Google Scholar
- 25.Joachims T (2005) A support vector method for multivariate performance measures. In: Proceedings of the 22nd international conference on machine learning, pp 377–384Google Scholar
- 27.Deb K, Goyal M (1996) A combined genetic adaptive search (geneas) for engineering design. Comput Sci Inform 26(4):30–45Google Scholar