Abstract
Case-based classification is normally based on similarity between a query and class members in the case base. This paper proposes a difference-based approach, class-to-class siamese network (C2C-SN) classification, in which classification is based on learning patterns of both similarity and difference between classes. A C2C-SN learns patterns from one class \(C_i\) to another class \(C_j\). The network can then be used, given two cases, to determine whether their similarity and difference conform to the learned patterns. If they do, it provides evidence for their belonging to the corresponding classes. We demonstrate the use of C2C-SNs for classification, explanation, and prototypical case finding. We demonstrate that C2C-SN classification can achieve good accuracy for case pairs, with the benefit of one-shot learning inherited from siamese networks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ashley, K., Rissland, E.: Compare and contrast, a test of expertise. In: Proceedings of the Sixth Annual National Conference on Artificial Intelligence, AAAI, pp. 273–284. Morgan Kaufmann, San Mateo (1987)
Bareiss, R.: Exemplar-Based Knowledge Acquisition: A Unified Approach to Concept Representation, Classification, and Learning. Academic Press, San Diego (1989)
Bromley, J., et al.: Signature verification using a siamese time delay neural network. Int. J. Pattern Recogn. Artif. Intell. 7(04), 669–688 (1993)
Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., Shah, R.: Signature verification using a “siamese” time delay neural network. In: Proceedings of the 6th International Conference on Neural Information Processing Systems, NIPS 1993, pp. 737–744. Morgan Kaufmann Publishers Inc., San Francisco (1993)
Chollet, F., et al.: MNIST siamese (2015), code retrieved from keras.io. https://keras.io/examples/mnist_siamese/
Cunningham, P., Doyle, D., Loughrey, J.: An evaluation of the usefulness of case-based explanation. In: Ashley, K.D., Bridge, D.G. (eds.) ICCBR 2003. LNCS (LNAI), vol. 2689, pp. 122–130. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-45006-8_12
Doyle, D., Cunningham, P., Bridge, D., Rahman, Y.: Explanation oriented retrieval. In: Funk, P., González Calero, P.A. (eds.) ECCBR 2004. LNCS (LNAI), vol. 3155, pp. 157–168. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-28631-8_13
Gunning, D., Aha, D.W.: DARPA’s explainable artificial intelligence program. AI Mag. 40(2), 44–58 (2019)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, vol. 2, p. 17351742. IEEE Computer Society, USA (2006)
Kapetanakis, S., Martin, K., Wijekoon, A., Amin, K., Massie, S. (eds.): Proceedings of the ICCBR-19 Case Based Reasoning and Deep Learning Workshop CBRDL-19 (2019)
Bach, K., Marling, C. (eds.): ICCBR 2019. LNCS (LNAI), vol. 11680. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29249-2
Keane, M.T., Kenny, E.M.: How case based reasoning explained neural networks: an XAI survey of post-hoc explanation-by-example in ANN-CBR twins. CoRR arxiv:1905.07186 (2019)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML 2015 Deep Learning Workshop (2015)
Leake, D.: CBR in context: the present and future. In: Leake, D. (ed.) Case-Based Reasoning: Experiences, Lessons, and Future Directions, pp. 3–30. AAAI Press, Menlo Park (1996)
Leake, D., Birnbaum, L., Hammond, K., Marlow, C., Yang, H.: An integrated interface for proactive, experience-based design support. In: Proceedings of the 2001 International Conference on Intelligent User Interfaces, pp. 101–108 (2001)
de Mántaras, R.L., et al.: Retrieval, reuse, revision, and retention in CBR. Knowl. Eng. Rev. 20(3), 215–240 (2005)
Marchiori, E.: Class dependent feature weighting and k-nearest neighbor classification. In: Ngom, A., Formenti, E., Hao, J.-K., Zhao, X.-M., van Laarhoven, T. (eds.) PRIB 2013. LNCS, vol. 7986, pp. 69–78. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-39159-0_7
Martin, K., Wiratunga, N., Sani, S., Massie, S., Clos, J.: A convolutional siamese network for developing similarity knowledge in the selfback dataset. In: ICCBR (Workshops) (2017)
Mathisen, B.M., Aamodt, A., Bach, K., Langseth, H.: Learning similarity measures from data. Prog. Artif. Intell. 9(2), 129–143 (2019). https://doi.org/10.1007/s13748-019-00201-2
Nugent, C., Doyle, D., Cunningham, P.: Gaining insight through case-based explanation. J. Intell. Inf. Syst. 32, 267–295 (2009)
Research, Z.: Fashion MNIST (2020), data retrieved from Kaggle. https://www.kaggle.com/zalando-research/fashionmnist
Tversky, A.: Features of similarity. Psychol. Rev. 84(4), 327–352 (1977)
Wettschereck, D., Aha, D., Mohri, T.: A review and empirical evaluation of feature-weighting methods for a class of lazy learning algorithms. Artif. Intell. Rev. 11(1–5), 273–314 (1997)
Ye, X.: The enemy of my enemy is my friend: class-to-class weighting in k-nearest neighbors algorithm. In: Proceedings of the Thirty-First International Florida Artificial Intelligence Research Society Conference, FLAIRS, vol. 2018, pp. 389–394 (2018)
Ye, X.: C2C trace retrieval: fast classification using class-to-class weighting. In: Proceedings of the Thirty-Second International Florida Artificial Intelligence Research Society Conference, FLAIRS, vol. 2019, pp. 353–358 (2019)
Acknowledgment
This material is based upon work supported in part by the Department of the Navy, Office of Naval Research under award number N00014-19-1-2655.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ye, X., Leake, D., Huibregtse, W., Dalkilic, M. (2020). Applying Class-to-Class Siamese Networks to Explain Classifications with Supportive and Contrastive Cases. In: Watson, I., Weber, R. (eds) Case-Based Reasoning Research and Development. ICCBR 2020. Lecture Notes in Computer Science(), vol 12311. Springer, Cham. https://doi.org/10.1007/978-3-030-58342-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-58342-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58341-5
Online ISBN: 978-3-030-58342-2
eBook Packages: Computer ScienceComputer Science (R0)