Abstract
Active learning differs from the training–testing scenario in that class labels can be obtained upon request. It is widely employed in applications where the labeling of instances incurs a heavy manual cost. In this paper, we propose a new algorithm called tri-partition active learning through k-nearest neighbors (TALK). The optimization objective is to minimize the total teacher and misclassification costs. First, a k-nearest neighbors classifier is employed to divide unlabeled instances into three disjoint regions. Region I contains instances for which the expected misclassification cost is lower than the teacher cost, Region II contains instances to be labeled by human experts, and Region III contains the remaining instances. Various strategies are designed to determine which instances are in Region II. Second, instances in Regions I and II are labeled and added to the training set, and the tri-partition process is repeated until all instances have been labeled. Experiments are undertaken on eight University of California, Irvine, datasets using different cost settings. Compared with the state-of-the-art cost-sensitive classification and active learning algorithms, our new algorithm generally exhibits a lower total cost.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aha DW (1997) Lazy learning. Artif Intell Rev 11:7–10
Basu S (2010) Semi-supervised learning. J Roy Stat Soc 6493(10):2465–2472
Blake C, Merz CJ (1998) UCI repository of machine learning databases
Bradford JP, Kunz C, Kohavi R, Brunk C, Brodley CE (2006) Pruning decision trees with misclassification costs. Lect Notes Comput Sci 51(1398):131–136
Brighton H, Mellish C (2001) Identifying competence-critical instances for instance-based learners. Springer 608:77–94
Cai D, He X (2012) Manifold adaptive experimental design for text categorization. IEEE Trans Knowl Data Eng 24(4):707–719
Dasgupta S, Hsu D (2008) Hierarchical sampling for active learning. In: International conference on machine learning, pp 208–215
Guo G, Wang H, Bell D, Bi Y, Greer K (2004) KNN model-based approach in classification. Springer, Berlin
Harpale AS, Yang Y (2008) Personalized active learning for collaborative filtering. In: International ACM SIGIR conference on research and development in information retrieval, pp 91–98
He YW, Zhang HR, Min F (2015) A teacher-cost-sensitive decision-theoretic rough set model. Springer, New York
Jin R, Si L (2004) A bayesian approach toward active learning for collaborative filtering, pp 278–285
Lesot MJ, Rifqi M, Benhadda H (2009) Similarity measures for binary and numerical data: a survey. Int J Knowl Eng Soft Data Paradig 1(1):63–84
Li HX, Zhang LB, Huang B, Zhou XZ (2016) Sequential three-way decision and granulation for cost-sensitive face recognition. Knowl Based Syst 91:241–251
Li JH, Ren Y, Mei CL, Qian YH, Yang XB (2016) A comparative study of multigranulation rough sets and concept lattices via rule acquisition. Knowl Based Syst 91:152–164
Li XN, Yi HJ, She YH, Sun BZ (2017) Generalized three-way decision models based on subset evaluation. Int J Approximate Reasoning 83:142–159
Liu D, Li TR, Ruan D (2011) Probabilistic model criteria with decision-theoretic rough sets. Inf Sci 181:3709–3722
Liu D, Li TR, Liang DC (2014) Incorporating logistic regression to decision-theoretic rough sets for classifications. Int J Approx Reason 55:197–210
Liu D, Liang D, Wang C (2016) A novel three-way decision model based on incomplete information system. Knowl-Based Syst 91:32–45
Long B, Bian J, Chapelle O, Zhang Y (2015) Active learning for ranking through expected loss optimization. IEEE Trans Knowl Data Eng 27(5):1180–1191
Long B, Chapelle O, Zhang Y, Chang Y, Zheng Z, Tseng B (2010) Active learning for ranking through expected loss optimization. In: Proceeding of the international ACM SIGIR conference on research and development in information retrieval, SIGIR 2010, Geneva, Switzerland, pp 267–274
Mccallum A, Nigam K (1998) Employing EM and pool-based active learning for text classification. In: Fifteenth international conference on machine learning, pp 350–358
Min F, Liu QH (2009) A hierarchical model for test-cost-sensitive decision systems. Inf Sci 179:2442–2452
Quinlan JR (1986) Induction of decision trees. Mach Learn 1(1):81–106
Quinlan JR (2014) C.45: programs for machine learning. Elsevier, Amsterdam
Rand GK (1979) Decision systems for inventory management and production planning. Wiley, New York
Saartsechansky M, Provost F (2004) Active sampling for class probability estimation and ranking. Mach Learn 54(2):153–178
Settles B (2012) Active learning. Synth Lect Artif Intell Mach Learn 6(1):1–114
Seung HS, Opper M, Sompolinsky H (1992) Query by committee. In: Proceedings of the fifth workshop on computational learning theory, vol 284, pp 287–294
Sheng VS (2012) Studying active learning in the cost-sensitive framework. In: Hawaii international conference on system sciences, pp 1097–1106
Tong S, Koller D (2001) Support vector machine active learning with applications to text classification. J Mach Learn Res 2(1):45–66
Turney PD (2000) Types of cost in inductive concept learning. In: Proceedings of the workshop on cost-sensitive learning at the 17th ICML, pp 1–7
Wang M, Min F, Zhang ZH, Wu YX (2017) Active learning through density clustering. Expert Syst Appl 85:305–317
Yao YY (2012) An outline of a theory of three-way decisions. In: International conference on rough sets and current trends in computing, Springer, New York, pp 1–17
Yao YY (2016) Three-way decisions and cognitive computing. Cognit Comput 8(4):543–554
Yao YY (2010) Three-way decisions with probabilistic rough sets. Inf Sci 180(3):341–353
Zhang HR, Min F, Shi B (2016) Regression-based three-way recommendation. Inf Sci
Zhang HR, Min F (2016) Three-way recommender systems based on random forests. Knowl Based Syst 91:275–286
Zhang BW, Min F, Ciucci D (2015) Representative-based classification through covering-based neighborhood rough sets. Appl Intell 43(4):840–854
Zhang Y, Zhou ZH (2008) Cost-sensitive face recognition. In: IEEE conference on computer vision and pattern recognition, pp 1–8
Zhao H, Zhu W (2014) Optimal cost-sensitive granularization based on rough sets for variable costs. Knowl Based Syst 65:72–82
Zhao Y, Yao Y, Luo F (2007) Data analysis based on discernibility and indiscernibility. Inf Sci 177(22):4959–4976
Zhao H, Wang P, Hu QH (2016) Cost-sensitive feature selection based on adaptive neighborhood granularity with multi-level confidence. Inf Sci 366:134–149
Zhou ZH, Liu XY (2006) Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Trans Knowl Data Eng 18(1):63–77
Zhou B, Yao Y, Luo J (2014) Cost-sensitive three-way email spam filtering. J Intell Inf Syst 42(1):19–45
Zhu XQ, Wu XD (2005) Cost-constrained data acquisition for intelligent data preparation. IEEE Trans Knowl Data Eng 17(11):1542–1556
Acknowledgements
This work is supported in part by National Natural Science Foundation of China (Grant No. 61379089) and the Natural Science Foundation of Department of Education of Sichuan Province (Grant No. 16ZA0060).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interests regarding the publication of this paper.
Additional information
Communicated by V. Loia.
Rights and permissions
About this article
Cite this article
Min, F., Liu, FL., Wen, LY. et al. Tri-partition cost-sensitive active learning through kNN. Soft Comput 23, 1557–1572 (2019). https://doi.org/10.1007/s00500-017-2879-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-017-2879-x