Abstract
Since the widespread adoption of deep learning solutions in critical environments, the interpretation of artificial neural networks has become a significant issue. To this end, numerous approaches currently try to align human-level concepts with the activation patterns of artificial neurons. Nonetheless, they often understate two related aspects: the distributed nature of neural representations and the semantic relations between concepts. We explicitly tackled this interrelatedness by defining a novel semantic alignment framework to align distributed activation patterns and structured knowledge. In particular, we detailed a solution to assign to both neurons and their linear combinations one or more concepts from the WordNet semantic network. Acknowledging semantic links also enabled the clustering of neurons into semantically rich and meaningful neural circuits. Our empirical analysis of popular convolutional networks for image classification found evidence of the emergence of such neural circuits. Finally, we discovered neurons in neural circuits to be pivotal for the network to perform effectively on semantically related tasks. We also contribute by releasing the code that implements our alignment framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Araujo, A., Norris, W., Sim, J.: Computing receptive fields of convolutional neural networks. Distill (2019). https://doi.org/10.23915/distill.00021, https://distill.pub/2019/computing-receptive-fields
Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017
Deng, J., Dong, W., Socher, R., Li, L., Kai Li, Li Fei-Fei: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009). https://doi.org/10.1109/CVPR.2009.5206848
Euzenat, J., Shvaiko, P.: Classifications of Ontology Matching Techniques. In: In: Ontology Matching, pp. 73–84. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38721-0_4
Euzenat, J., Shvaiko, P.: The Matching Problem. In: In: Ontology Matching, pp. 25–54. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38721-0_2
Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3449–3457, October 2017. https://doi.org/10.1109/ICCV.2017.371, iSSN: 2380-7504
Frege, G.: Function und Begriff. Hermann Pohle, Jena (1891)
Goh, G., et al.: Multimodal neurons in artificial neural networks. Distill (2021). https://doi.org/10.23915/distill.00030. https://distill.pub/2021/multimodal-neurons
Guarino, N., Oberle, D., Staab, S.: What is an ontology? In: Staab, S., Studer, R. (eds.) Handbook on Ontologies. IHIS, pp. 1–17. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-540-92673-3_0
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51(5), 1–42 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015). http://arxiv.org/abs/1512.03385
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Jiang, J.J., Conrath, D.W.: Semantic similarity based on corpus statistics and lexical taxonomy. In: Proceedings of the 10th Research on Computational Linguistics International Conference, pp. 19–33. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP), Taipei, Taiwan, August 1997. https://aclanthology.org/O97-1002
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., Sayres, R.: Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV). arXiv:1711.11279 [stat], June 2018. http://arxiv.org/abs/1711.11279,arXiv: 1711.11279
Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. CoRR abs/1404.5997 (2014). http://arxiv.org/abs/1404.5997
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Miller, G.A.: Wordnet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)
Miller, G.A., Hristea, F.: Wordnet nouns: classes and instances. Comput. Linguist. 32(1), 1–3 (2006). https://doi.org/10.1162/coli.2006.32.1.1
Mu, J., Andreas, J.: Compositional explanations of neurons. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 17153–17163. Curran Associates, Inc. (2020). https://proceedings.neurips.cc/paper/2020/file/c74956ffb38ba48ed6ce977af6727275-Paper.pdf
Olah, C., Cammarata, N., Schubert, L., Goh, G., Petrov, M., Carter, S.: Zoom. In: An introduction to circuits. Distill (2020). https://doi.org/10.23915/distill.00024.001. https://distill.pub/2020/circuits/zoom-in
Olah, C., Mordvintsev, A., Schubert, L.: Feature visualization. Distill (2017). https://doi.org/10.23915/distill.00007. https://distill.pub/2017/feature-visualization
Otero-Cerdeira, L., Rodríguez-Martínez, F.J., Gómez-Rodríguez, A.: Ontology matching: a literature review. Expert Syst. Appl. 42(2), 949–971 (2015)
Page, M.: Connectionist modelling in psychology: a localist manifesto. Behavioral Brain Sci. 23(4), 443–467 (2000). https://doi.org/10.1017/S0140525X00003356
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Zhou, B., Khosla, A., Lapedriza, À., Oliva, A., Torralba, A.: Object detectors emerge in deep scene cnns. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9, May 2015, Conference Track Proceedings (2015). http://arxiv.org/abs/1412.6856
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2017)
Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014). https://proceedings.neurips.cc/paper/2014/file/3fe94a002317b5f9259f82690aeea4cd-Paper.pdf
Zhou, B., Sun, Y., Bau, D., Torralba, A.: Interpretable basis decomposition for visual explanation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_8
Zhou, B., Sun, Y., Bau, D., Torralba, A.: Revisiting the importance of individual units in cnns via ablation. CoRR abs/1806.02891 (2018). http://arxiv.org/abs/1806.02891
Acknowledgments
This research was partially supported by TAILOR, a project funded by EU Horizon 2020 research and innovation programme under GA No 952215.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Massidda, R., Bacciu, D. (2023). Knowledge-Driven Interpretation of Convolutional Neural Networks. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13713. Springer, Cham. https://doi.org/10.1007/978-3-031-26387-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-26387-3_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26386-6
Online ISBN: 978-3-031-26387-3
eBook Packages: Computer ScienceComputer Science (R0)