Skip to main content
SpringerLink
Log in

Incremental sequential three-way decision based on continual learning network

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Continual learning has attracted much attention in recent years, and many continual learning methods based on deep neural networks have been proposed. However, several important problems about these methods may lead to high decision cost and affect the practical application of continual learning networks. First, continual learning networks treat all categories equally, although the unbalance of misclassification cost happens in real-world cases. Second, there is a trade-off between learning new knowledge and keep old knowledge, which leads to the forgetting of old knowledge (i.e., the catastrophic forgetting). Third, even if low confidence of a sample, the continual learning methods based on the neural network will still give a clear classification result. We propose a sequential three-way decision model for continual learning to address these problems, named Incremental Sequential Three-Way Decision model (ISTWD). Introducing cost-sensitive sequential three-way decision to continual learning network, ISTWD reduces the decision cost of continual learning, which may alleviate the potentially high cost caused by the accuracy loss in continual learning. Besides, ISTWD includes a checkpoint procedure to judge whether the process of continual learning should stop. Experimental results on CIFAR-100 and Tiny-ImageNet verify the effectiveness of our method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Yao YY (2009) Three-way decision: an interpretation of rules in rough set theory. In: International conference on rough sets and knowledge technology, pp 642–649

  2. Yao YY (2018) Three-way decision and granular computing. Int J Approx Reason 103:107–123

    Article  Google Scholar 

  3. Yao YY (2019) Three-way conflict analysis: reformulations and extensions of the pawlak model. Knowl-Based Syst 180:26–37

    Article  Google Scholar 

  4. Yang JL, Yao YY (2020) Semantics of soft sets and three-way decision with soft sets. Knowl-Based Syst 194:105538

    Article  Google Scholar 

  5. Zhan JM, Jiang HB, Yao YY (2020) Three-way multi-attribute decision-making based on outranking relations. IEEE Trans Fuzzy Syst 13(8):1384

    Google Scholar 

  6. Liu JB, Li HX, Zhou XZ, Huang B, Wang TX (2019) An optimization-based formulation for three-way decisions. Inf Sci 495:185–214

    Article  Google Scholar 

  7. Liu JB, Li HX, Huang B, Liu Y, Liu D (2021) Convex combination-based consensus analysis for intuitionistic fuzzy three-way group decision. Inf Sci 574:542–566

    Article  MathSciNet  Google Scholar 

  8. Yao YY, Deng XF (2011) Sequential three-way decisions with probabilistic rough sets. In: International conference on cognitive informatics and cognitive computing, pp 120–125

  9. Li HX, Zhang LB, Zhou XZ, Huang B (2017) Cost-sensitive sequential three-way decision modeling using a deep neural network. Int J Approx Reason 85:68–78

    Article  MathSciNet  Google Scholar 

  10. Li HX, Zhang LB, Huang B, Zhou XZ (2020) Cost-sensitive dual-bidirectional linear discriminant analysis. Inf Sci 510:283–303

    Article  MathSciNet  Google Scholar 

  11. Liang DC, Liu D (2014) A novel risk decision making based on decision-theoretic rough sets under hesitant fuzzy information. IEEE Trans Fuzzy Syst 23(2):237–247

    Article  MathSciNet  Google Scholar 

  12. Savchenko AV (2019) Sequential three-way decisions in multi-category image recognition with deep features based on distance factor. Inf Sci 489:18–36

    Article  MathSciNet  Google Scholar 

  13. Hao C, Li JH, Fan M, Liu WQ, Tsang EC (2017) Optimal scale selection in dynamic multi-scale decision tables based on sequential three-way decisions. Inf Sci 415:213–232

    Article  Google Scholar 

  14. Yang X, Li TR, Fujita H, Liu D (2019) A sequential three-way approach to multi-class decision. Int J Approx Reason 104:108–125

    Article  MathSciNet  Google Scholar 

  15. Qian J, Liu CH, Yue XD (2019) Multigranulation sequential three-way decisions based on multiple thresholds. Int J Approx Reason 105:396–416

    Article  MathSciNet  Google Scholar 

  16. Zhang LB, Li HX, Zhou XZ, Huang B (2020) Sequential three-way decision based on multi-granular autoencoder features. Inf Sci 507:630–643

    Article  Google Scholar 

  17. 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

    Article  Google Scholar 

  18. French RM (1999) Catastrophic forgetting in connectionist networks. Trends Cogn Sci 3(4):128–135

    Article  Google Scholar 

  19. Goodfellow IJ, Mirza M, Xiao D, Courville A, Bengio Y (2013) An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv: 13126211

  20. Parisi GI, Kemker R, Part JL, Kanan C, Wermter S (2019) Continual lifelong learning with neural networks: a review. Neural Netw 113:54–71

    Article  Google Scholar 

  21. Qian YH, Liang XY, Lin GP, Guo Q, Liang JY (2017) Local multigranulation decision-theoretic rough sets. Int J Approx Reason 82:119–137

    Article  MathSciNet  Google Scholar 

  22. Li JH, Huang CC, Qi JJ, Qian YH, Liu WQ (2017) Three-way cognitive concept learning via multi-granularity. Inf Sci 378:244–263

    Article  Google Scholar 

  23. Liu D, Li TR, Liang DC (2014) Incorporating logistic regression to decision-theoretic rough sets for classifications. Int J Approx Reason 55(1):197–210

    Article  MathSciNet  Google Scholar 

  24. Min F, Zhang ZH, Zhai WJ, Shen RP (2020) Frequent pattern discovery with tri-partition alphabets. Inf Sci 507:715–732

    Article  MathSciNet  Google Scholar 

  25. Yao JT, Azam N (2014) Web-based medical decision support systems for three-way medical decision making with game-theoretic rough sets. IEEE Trans Fuzzy Syst 23(1):3–15

    Article  Google Scholar 

  26. Huang B, Guo CX, Li HX, Feng GF, Zhou XZ (2016) Hierarchical structures and uncertainty measures for intuitionistic fuzzy approximation space. Inf Sci 336:92–114

    Article  Google Scholar 

  27. Liu D, Ye XQ (2020) A matrix factorization based dynamic granularity recommendation with three-way decisions. Knowl-Based Syst 191:105423

    Google Scholar 

  28. Yu H, Zhang C, Wang GY (2016) A tree-based incremental overlapping clustering method using the three-way decision theory. Knowl-Based Syst 91:189–203

    Article  Google Scholar 

  29. Yu H (2018) Three-way decisions and three-way clustering. In: International joint conference on rough sets, pp 13–28

  30. Min F, Zhang SM, Ciucci D, Wang M (2020) Three-way active learning through clustering selection. Int J Mach Learn Cybern 11(5):1033–1046

    Article  Google Scholar 

  31. Liu D, Liang DC, Wang CC (2016) A novel three-way decision model based on incomplete information system. Knowl-Based Syst 91:32–45

    Article  Google Scholar 

  32. Wu WZ, Qian YH, Li TJ, Gu SM (2017) On rule acquisition in incomplete multi-scale decision tables. Inf Sci 378:282–302

    Article  MathSciNet  Google Scholar 

  33. Liu D, Yang X, Li TR (2020) Three-way decisions: beyond rough sets and granular computing. Int J Mach Learn Cybern 11(5):989–1002

    Article  Google Scholar 

  34. Li JH, Liu ZM (2020) Granule description in knowledge granularity and representation. Knowl-Based Syst 203:106160

    Article  Google Scholar 

  35. Shin H, Lee JK, Kim J, Kim J (2017) Continual learning with deep generative replay. arXiv preprint arXiv: 170508690

  36. Delange M, Aljundi R, Masana M, Parisot S, Jia X, Leonardis A, Slabaugh G, Tuytelaars T (2021) A continual learning survey: defying forgetting in classification tasks. IEEE Trans Pattern Anal Mach Intell 10.1109/TPAMI20213057446

  37. Cichon J, Gan WB (2015) Branch-specific dendritic ca 2+ spikes cause persistent synaptic plasticity. Nature 520(7546):180–185

    Article  Google Scholar 

  38. Kirkpatrick J, Pascanu R, Rabinowitz N, Veness J, Desjardins G, Rusu AA, Milan K, Quan J, Ramalho T, Grabska-Barwinska A et al (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci 114(13):3521–3526

    Article  MathSciNet  Google Scholar 

  39. Schwarz J, Czarnecki W, Luketina J, Grabska-Barwinska A, Teh YW, Pascanu R, Hadsell R (2018) Progress & compress: a scalable framework for continual learning. In: International conference on machine learning, pp 4528–4537

  40. Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533

    Article  Google Scholar 

  41. Rebuffi SA, Kolesnikov A, Sperl G, Lampert CH (2017) icarl: Incremental classifier and representation learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2001–2010

  42. Li ZZ, Hoiem D (2017) Learning without forgetting. IEEE Trans Pattern Anal Mach Intell 40(12):2935–2947

    Article  Google Scholar 

  43. He KM, Zhang XY, Ren SQ, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  44. Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv preprint arXiv: 150302531

  45. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211–252

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgements

This work was partially supported by National Natural Science Foundation of China (Nos. 62176116, 71732003, 61773208) and the National Key Research and Development Program of China (No. 2018YFB1402600).

Author information

Authors and Affiliations

  1. Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, 210093, China

    Hongyuan Li & Huaxiong Li

  2. College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China

    Hong Yu

  3. School of Computer Science, Southwest Petroleum University, Chengdu, 610500, China

    Fan Min

  4. School of Economics and Management, Southwest Jiaotong University, Chengdu, 610031, China

    Dun Liu

Authors
  1. Hongyuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hong Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fan Min
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dun Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Huaxiong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Huaxiong Li.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, H., Yu, H., Min, F. et al. Incremental sequential three-way decision based on continual learning network. Int. J. Mach. Learn. & Cyber. 13, 1633–1645 (2022). https://doi.org/10.1007/s13042-021-01472-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-021-01472-9

Keywords

Search

Navigation