Abstract
In system modeling, traditional machine learning methods aim to make a model’s output fit the real output as well as possible. However, sometimes they fail to reach the goal, especially when the quantity of samples is small (which often leads to the occurrence of overfitting). Therefore, researchers start to explore new approaches for system modeling with few samples. An effective alternative to solve this problem is to reduce the fitting expectation and make predictions from a certain range of samples. Granular computing techniques simulate human’s thinking rules at a higher level and thus can be applied to few samples learning (FSL). In this paper, we realize granular neural network (GNN) modeling with few samples. A conceptually simple yet powerful method to learn some coarse-grained information from few samples is proposed. The output of the GNN model is fuzzy (represented by information granules). It can predict a new sample’s output with a rough range which makes the model own stronger robustness especially when the quantity of training samples is small. The precondition is that it is not necessary to accurately determine the explicit output of the samples. In the experiment, we compare the coverage of the models on the same test set in which the models are built using different percentage of training samples. The results show that the model built on few samples can also achieve good performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Benedicenti L, Blachford D, Chan C, East A, Gelowitz C, Huang G, Paranjape R, Petty S, Yao J, Yao Y (2013) Multidisciplinary approaches to computing. In: 2013 26th IEEE Canadian conference on electrical and computer engineering (CCECE), IEEE, pp 1–8
Chukhrova N, Johannssen A (2019) Fuzzy regression analysis: systematic review and bibliography. Appl Soft Comput 84:105708
Ciavolino E, Calcagnì A (2016) A generalized maximum entropy (GME) estimation approach to fuzzy regression model. Appl Soft Comput 38:51–63. https://doi.org/10.1016/j.asoc.2015.08.061
Dai W, Chen Y, Xue G-R, Yang Q, Yu Y (2008) Translated learning: transfer learning across different feature spaces. Adv Neural Inf Process Syst 21:353–360
Fei-Fei L, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell 28:594–611
Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of ICNN’95-international conference on neural networks, IEEE, pp 1942–1948
Lee S-I, Chatalbashev V, Vickrey D, Koller D (2007) Learning a meta-level prior for feature relevance from multiple related tasks. In: Proceedings of the 24th international conference on machine learning, pp 489–496
Li W, Wang J, Chen K, Li W (2017) An intelligent cognition method of human health states based on a variant knowledge granularity feedback mechanism. IEEE Access 5:19570–19580
Lin TY (2009) Granular computing: practices, theories, and future directions. Encycl Complex Syst Sci 2009:4339–4355
Miller EG, Matsakis NE, Viola PA (2000) Learning from one example through shared densities on transforms. In: Proceedings IEEE conference on computer vision and pattern recognition. CVPR 2000 (Cat. No. PR00662), IEEE, pp 464–471
Min F, Zhu W (2013) Mining top-k granular association rules for recommendation. arXiv preprint arXiv:13054801
Pedrycz W (2015) Concepts and design aspects of granular models of type-1 and type-2. Int J Fuzzy Log Intell Syst 15:87–95
Pedrycz W, Vukovich G (2001) Granular neural networks. Neurocomputing 36:205–224. https://doi.org/10.1016/S0925-2312(00)00342-8
Qi G-J, Aggarwal C, Huang T (2011) Towards semantic knowledge propagation from text corpus to web images. In: Proceedings of the 20th international conference on world wide web, pp 297–306
Rodner E (2012) Visual transfer learning: informal introduction and literature overview. arXiv preprint arXiv:12111127
Rodner E, Denzler J (2010) One-shot learning of object categories using dependent gaussian processes. In: Joint Pattern Recognition Symposium, Springer, pp 232–241
Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:160506065
Seraya OV, Demin DA (2012) Linear regression analysis of a small sample of fuzzy input data. J Autom Inf Sci 44:34–48. https://doi.org/10.1615/JAutomatInfScien.v44.i7.40
Song M, Pedrycz W (2013) Granular neural networks: concepts and development schemes. IEEE Trans Neural Netw Learn Syst 24:542–553
Song J, Yang X, Qi Y, Yu H, Song X, Yang J (2014) Characterizing hierarchies on covering-based multigranulation spaces. Rough sets and knowledge technology. Springer, Cham, pp 467–478
Tan C, Sun F, Kong T, Zhang W, Yang C, Liu C (2018) A survey on deep transfer learning. Artificial neural networks and machine learning – ICANN 2018. Springer, Cham, pp 270–279
Tommasi T (2013) Learning to learn by exploiting prior knowledge. Ph.D. Dissertation, Swiss federal Institute of Technology in Lausanne
van den Bergh F, Engelbrecht AP (2006) A study of particle swarm optimization particle trajectories. Inf Sci 176:937–971
Wang G, Yang J, Xu J (2017) Granular computing: from granularity optimization to multi-granularity joint problem solving. Granul Comput 2:105–120. https://doi.org/10.1007/s41066-016-0032-3
Wei T, Hou J, Feng R (2020) Fuzzy graph neural network for few-shot learning. In: 2020 International joint conference on neural networks (IJCNN), pp 1–8
Wu Q, Law R (2010) Fuzzy support vector regression machine with penalizing Gaussian noises on triangular fuzzy number space. Expert Syst Appl 37:7788–7795
Yang Q, Liu Y, Cheng Y, Kang Y, Chen T, Yu H (2019) Federated learning. Synth Lect Artif Intell Mach Learn 13:1–207
Yao Y (2008) Granular computing: past, present and future. In: 2008 IEEE international conference on granular computing, pp 80–85
Yao JT, Vasilakos AV, Pedrycz W (2013) Granular computing: perspectives and challenges. IEEE Trans Cybern 43:1977–1989
Yu Y, Zhang K, Wang J (2015) Bidding behavior evaluation using fuzzy evidential reasoning and, belief rule-based approach. In: 2015 International conference on control, electronics, renewable energy and communications (ICCEREC), IEEE, pp 148–152
Zadeh LA (1979) Fuzzy sets and information granularity. Adv Fuzzy Set Theory Appl 11:3–18
Zhan J, Jiang H, Yao Y (2020) Three-way multi-attribute decision-making based on outranking relations. IEEE Trans Fuzzy Syst. https://doi.org/10.1109/TFUZZ.2020.3007423
Zhan J, Ye J, Ding W, Liu P (2021) A novel three-way decision model based on utility theory in incomplete fuzzy decision systems. IEEE Trans Fuzzy Syst 1–1
Zhang Y, Yang Q (2021) A survey on multi-task learning. arXiv:170708114 [cs]
Zhang K, Zhan J, Wu W-Z (2020) On multi-criteria decision-making method based on a fuzzy rough set model with fuzzy α-neighborhoods. IEEE Trans Fuzzy Syst 1–1
Zhao C, Chen F (2020) Unfairness discovery and prevention for few-shot regression. In: 2020 IEEE international conference on knowledge graph (ICKG), IEEE, Nanjing, China, pp 137–144
Zhu Y, Chen Y, Lu Z, Pan S, Xue G-R, Yu Y, Yang Q (2011) Heterogeneous transfer learning for image classification. In: Proceedings of the AAAI conference on artificial intelligence
Acknowledgements
The valuable comments from anonymous referees are gratefully appreciated. Support from the National Natural Science Foundation of China (NSFC) 61773352 is also gratefully appreciated.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, Y., Song, M. Few samples learning based on granular neural networks. Granul. Comput. 7, 577–589 (2022). https://doi.org/10.1007/s41066-021-00285-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41066-021-00285-z