Abstract
In this paper we introduce an explanation technique for Convolutional Neural Networks (CNNs) based on the theory of causality by Halpern and Pearl [12]. The causal explanation technique (CexCNN) is based on measuring the filter importance to a CNN decision, which is measured through counterfactual reasoning. In addition, we employ extended definitions of causality, which are responsibility and blame to weight the importance of such filters and project their contribution on input images. Since CNNs form a hierarchical structure, and since causal models can be hierarchically abstracted, we employ this similarity to perform the most important contribution of this paper, which is localizing the important features in the input image that contributed the most to a CNN’s decision. In addition to its ability in localization, we will show that CexCNN can be useful as well for model compression through pruning the less important filters. We tested CexCNN on several CNNs architectures and datasets. (The code is available on https://github.com/HichemDebbi/CexCNN)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Investigate. https://github.com/albermax/innvestigate
keras-surgeon. https://github.com/BenWhetton/keras-surgeon
Keras visualization toolkit. https://github.com/raghakot/keras-vis
Avanti, S., Peyton, G., Anshul, K.: Learning important features through propagating activation differences, pp. 3145–3153. ICML’17 (2017)
Beckers, S., Halpern, J.Y.: Abstracting causal models. In: AAAI (2017)
Chockler, H., Halpern, J.Y.: Responsibility and blame: a structural-model approach. J. Artif. Int. Res. 22(1), 93–115 (2004)
Choe, J., Oh, S.J., Lee, S., Chun, S., Akata, Z., Shim, H.: Evaluating weakly supervised object localization methods right. In: CVPR, pp. 3130–3139 (2020)
Gordon, D., Kembhavi, A., Rastegari, M., Redmon, J., Fox, D., Farhadi, A.: Iqa: visual question answering in interactive environments. In: In arXiv:1712.03316 (2017)
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580–587 (2014)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICLR (2015)
Halpern, J., Pearl, J.: Causes and explanations: a structural-model approach part i: Causes. In: Proceedings of the 17th UAI, pp. 194–202 (2001)
Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. part ii: Explanations. Br. J. Philos. Sci. 56(4), 889–911 (2008)
Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. In: NIPS (2015)
Harradon, M., Druce, J., Ruttenberg, B.E.: Causal learning and explanation of deep neural networks via autoencoded activations. In: CoRR abs/1802.00541 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
LeCun, Y., Cortes, C., Burges, C.: Mnist handwritten digit database. ATT Labs [Online]. http://yann.lecun.com/exdb/mnist 2 (2010)
Lewis, D.: Causation. J. Philos. 70, 556–567 (1972)
Li, H., Kadav, A., Durdanovic, I., Samety, H.: Pruning filters for efficient convnets. In: ICLR 2017, pp. 1–13 (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: NIPS, pp. 4768–4777 (2017)
Molnar, C.: Interpretable Machine Learning A Guide for Making Black Box Models Explainable (2018). https://christophm.github.io/interpretable-ml-book/
Narendra, T., Sankaran, A., Vijaykeerthy, D., Mani, S.: Explaining deep learning models using causal inference. In: arXiv:1811.04376 (2018)
Ribeiro, M.T., Singh, S., Guestrin, C.: “why should i trust you?": Explaining the predictions of any classifier, pp. 1135–1144. KDD ’16 (2016)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Schwab, P., Karlen, W.: Cxplain: causal explanations for model interpretation under uncertainty. NeurIPS, pp. 10220–10230 (2019)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618–626 (2017)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: In arXiv:1312.6034 (2013)
Singh, K.K., Lee, Y.J.: Forcing a network to be meticulous for weakly-supervised object and action localization. In: CVPR (2017)
Smilkov, D., Thorat, N., Kim, B., Viegas, F.B., Wattenberg, M.: Smoothgrad: removing noise by adding noise. In: CoRR, vol. abs/1706.03825 (2017)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: ICML, pp. 3319–3328 (2017)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR, pp. 2921–2929 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Debbi, H. (2021). Causal Explanation of Convolutional Neural Networks. In: Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2021. Lecture Notes in Computer Science(), vol 12976. Springer, Cham. https://doi.org/10.1007/978-3-030-86520-7_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-86520-7_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86519-1
Online ISBN: 978-3-030-86520-7
eBook Packages: Computer ScienceComputer Science (R0)