Skip to main content
SpringerLink
Log in

Multi-granulation Multi-scale Relation Network for Abstract Reasoning

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

Abstract

Abstract reasoning, one of the representative works of logic learning, is to make machines intelligent. To test the intelligence of machines, researchers have proposed multiple benchmark data sets and these date sets mainly consist of a few simple geometries and traced reasoning paths. There are three issues for these data sets: (1) it is relatively easy for machines to reason the right answer from the simple geometries; (2) due to the limited number of geometric shapes, these data sets are prone to disclosure of information about reasoning; (3) all traced reasoning paths in these data sets have been known beforehand, some state-of-the-art reasoning models are specially designed according to these paths. Hence, these benchmark data sets cannot truly reflect the reasoning ability of reasoning models. To address these issues, we propose a Fashion Non-descending Path data set (FNP). FNP is designed using a mass of complex samples from Fashion-MNIST data set as objects of FNP and the non-descending path that is a more complex path as the variation directions of logical patterns. For gaining reasoning performance on FNP, inspired by the multi-granulation and multi-scale ideas, we propose a multi-granulation multi-scale relation network (M2RN) to consider the multi-wise relations rather than the simple pair-wise relations. Experimental results show that the M2RN is effective for abstract reasoning task.

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
Fig. 7

Similar content being viewed by others

References

  1. Liang X, Guo Q, Qian Y, Ding W, Zhang Q (2021) EDF: Evolutionary deep fusion method and its application in chemical structure recognition. IEEE Trans Evol Comput 25(5):883–893

  2. Liang X, Qian Y, Guo Q, Cheng H, Liang J (2021) AF: An association-based fusion method for multi-modal classification. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/TPAMI.2021.3125995

  3. Dai W-Z, Xu Q, Yu Y, Zhou Z-H (2019) Bridging machine learning and logical reasoning by abductive learning. In: 33rd conference on neural information processing systems (NeurIPS 2019), vol. 32. Vancouver, Canada, pp 2811–2822

  4. Huang Y-X, Dai W-Z, Yang J, Cai L-W, Cheng S, Huang R, Li Y-F, Zhou Z (2020) Semi-supervised abductive learning and its application to theft judicial sentencing. In: 2020 IEEE international conference on data mining (ICDM). pp 1070–1075. https://doi.org/10.1109/ICDM50108.2020.00127

  5. Guo Q, Qian Y, Liang X (2019) Mining logic patterns from visual data. In: 2019 IEEE international conference on data mining workshops (ICDMW). pp 620–627. https://doi.org/10.1109/ICDMW.2019.00094

  6. Santoro A, Hill F, Barrett D, Morcos A, Lillicrap T (2018) Measuring abstract reasoning in neural networks. In: International Conference on Machine Learning, pp 4477–4486

  7. Zhang C, Gao F, Jia B, Zhu Y, Zhu SC (2019) Raven: a dataset for relational and analogical visual reasoning. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 5312–5322, https://doi.org/10.1109/CVPR.2019.00546

  8. Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. eprintcs.LG/1708.07747

  9. Hoshen D, Werman M (2017) Iq of neural networks. CoRR. arXiv:1710.01692

  10. Jahrens M, Martinetz T (2019) Multi-layer relation networks for relational reasoning. pp 1–5, https://doi.org/10.1145/3309772.3309782

  11. Jahrens M, Martinetz T (2020) Solving raven’s progressive matrices with multi-layer relation networks. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp 1–6, https://doi.org/10.1109/IJCNN48605.2020.9207319

  12. Zheng K, Jun Zha Z, Wei W (2019) Abstract reasoning with distracting features. In: 33rd conference on neural information processing systems (NeurIPS 2019), vol 32. Vancouver, Canada, pp 5842–5853

  13. Santoro A, Raposo D, Barrett DG, Malinowski M, Pascanu R, Battaglia P, Lillicrap T (2017) A simple neural network module for relational reasoning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, USA, NIPS’17, pp 4974–4983

  14. Zadeh LA (1997) Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Syst 90(2):111–127

    Article  MathSciNet  Google Scholar 

  15. Wang J, Qian Y, Li F, Liang J, Ding W (2020) Fusing fuzzy monotonic decision trees. IEEE Trans Fuzzy Syst 28(5):887–900

    Article  Google Scholar 

  16. Wang Y, Hu Q, Zhu P, Li L, Lu B, Garibaldi JM, Li X (2020) Deep fuzzy tree for large-scale hierarchical visual classification. IEEE Trans Fuzzy Syst 28(7):1395–1406

    Google Scholar 

  17. Zhao H, Wang P, Hu Q, Zhu P (2019) Fuzzy rough set based feature selection for large-scale hierarchical classification. IEEE Trans Fuzzy Syst 27(10):1891–1903

    Article  Google Scholar 

  18. Hou W, Wang Y, Wang J, Cheng P, Li L (2021) Intuitionistic fuzzy c-means clustering algorithm based on a novel weighted proximity measure and genetic algorithm. Int J Mach Learn Cyber 12:859–875

    Article  Google Scholar 

  19. Li F, Qian Y, Wang J, Dang C, Jing L (2019) Clustering ensemble based on sample’s stability. Artif Intell 273:37–55

    Article  MathSciNet  Google Scholar 

  20. Yu H, Chen Y, Lingras P, Wang G (2019) A three-way cluster ensemble approach for large-scale data. Int J Approx Reason 115:32–49

    Article  MathSciNet  Google Scholar 

  21. Yu H, Chang Z, Wang G, Chen X (2020) An efficient three-way clustering algorithm based on gravitational search. Int J Mac Learn Cyber 11:1003–1016

    Article  Google Scholar 

  22. Cheng H, Qian Y, Hu Z, Liang J (2020) Association mining method based on neighborhood perspective. Scientia Sinica Informationis 50(6):824–844

    Article  Google Scholar 

  23. Jiang Z, Liu K, Yang X, Yu H, Fujita H, Qian Y (2020) Accelerator for supervised neighborhood based attribute reduction. Int J Approx Reason 119:122–150

    Article  MathSciNet  Google Scholar 

  24. Tawhid MA, Ibrahim AM (2020) Feature selection based on rough set approach, wrapper approach, and binary whale optimization algorithm. Int J Mach Learn Cyber 11:573–602

    Article  Google Scholar 

  25. Wang D, Chen H, Li T, Wan J, Huang Y (2020) A novel quantum grasshopper optimization algorithm for feature selection. Int J Approx Reason 127:33–53

    Article  MathSciNet  Google Scholar 

  26. Liu K, Yang X, Yu H, Hamidoand Fujita XLD, Chen X, (2020) Supervised information granulation strategy for attribute reduction. Int J Mach Learn Cyber 11:2149–2163

    Article  Google Scholar 

  27. Pang J, Guan X, Liang J, Wang B, Song P (2020) Multi-attribute group decision-making method based on multi-granulation weights and three-way decisions. Int J Approx Reason 117:122–147

    Article  MathSciNet  Google Scholar 

  28. Yang L, Xu W, Zhang X, Sang B (2020) Multi-granulation method for information fusion in multi-source decision information system. Int J Approx Reason 122:47–65

    Article  MathSciNet  Google Scholar 

  29. Ye D, Liang D, Li T, Liang S (2021) Multi-classification decision-making method for interval-valued intuitionistic fuzzy three-way decisions and its application in the group decision-making. Int J Mach Learn Cyber 12:661–687

    Article  Google Scholar 

  30. Qian Y, Liang J, Yao Y, Dang C (2010) MGRS: a multi-granulation rough set. Info Sci 180(6):949–970

    Article  MathSciNet  Google Scholar 

  31. Qian Y, Liang X, Lin G, Guo Q, Liang J (2017) Local multigranulation decision-theoretic rough sets. Int J Approx Reason 82:119–137

    Article  MathSciNet  Google Scholar 

  32. Qian Y, Liang J, Pedrycz W, Dang C (2010) Positive approximation: an accelerator for attribute reduction in rough set theory. Artif Intell 174(9–10):597–618

    Article  MathSciNet  Google Scholar 

  33. Wu W, Leung Y (2011) Theory and applications of granular labelled partitions in multi-scale decision tables. Info Sci 181(18):3878–3897

    Article  Google Scholar 

  34. Wu W, Qian Y, Li T, Gu S (2017) On rule acquisition in incomplete multi-scale decision tables. Info Sci 378:282–302

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgements

This work was supported by the Key Program of the National Natural Science Foundation of China (62136005), National Key R&D Program of China (No. 2018YFB1004300), National Natural Science Fund of China (No. 61432011, 61502289), Key R&D program (International Science and Technology Cooperation Project) of Shanxi Province, China (No. 201903D421003), Program for the Young San Jin Scholars of Shanxi (No. 2016769), Young Scientists Fund of the National Natural Science Foundation of China (No. 61802238, 61906115, 61603228, 62006146, 61906114), Shanxi Province Science Foundation for Youths (No. 201901D211169, 201901D211170, 201901D211171), Research Project Supported by Shanxi Scholarship Council of China (No. HGKY2019001), and Scientific and Technologial Innovation Programs of Higher Education Institutions in Shanxi (No. 2020L0036).

Author information

Authors and Affiliations

  1. Institute of Big Data Science and Industry, Shanxi University, Taiyuan, 030006, Shanxi, China

    Qian Guo, Yuhua Qian, Xinyan Liang, Junyu Chen & Honghong Cheng

  2. Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan, 030006, Shanxi, China

    Yuhua Qian

  3. School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, Shanxi, China

    Qian Guo, Yuhua Qian, Xinyan Liang & Junyu Chen

  4. School of Information, Shanxi University of Finance and Economics, Taiyuan, 030012, China

    Honghong Cheng

Authors
  1. Qian Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuhua Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xinyan Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Junyu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Honghong Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuhua Qian.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

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

Guo, Q., Qian, Y., Liang, X. et al. Multi-granulation Multi-scale Relation Network for Abstract Reasoning. Int. J. Mach. Learn. & Cyber. 13, 1751–1762 (2022). https://doi.org/10.1007/s13042-021-01484-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-021-01484-5

Keywords

Search

Navigation