Abstract
The interpretability of deep neural networks has aroused widespread concern in the academic and industrial fields. This paper proposes a new method named the dynamic reasoning and information bottleneck (DRIB) to improve human interpretability and understandability. In the method, a novel dynamic reasoning decision algorithm was proposed to reduce multiply accumulate operations and improve the interpretability of the calculation. The information bottleneck was introduced to the DRIB model to verify the attribution correctness of the dynamic reasoning module. The DRIB reduces the burden approximately 50% by decreasing the amount of computation. In addition, DRIB keeps the correct rate at approximately 93%. The information bottleneck theory verifies the effectiveness of this method, and the credibility is approximately 85%. In addition, through visual verification of this method, the highlighted area can reach 50% of the predicted area, which can be explained more obviously. Some experiments prove that the dynamic reasoning decision algorithm and information bottleneck theory can be combined with each other. Otherwise, the method provides users with good interpretability and understandability, making deep neural networks trustworthy.
Supported by National Natural Science Foundation of China [61972183].
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
References
Kim, Y.J., Bae, J.P., Chung, J.W., et al.: New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images. Sci. Rep. 11(1), 1–8 (2021)
Fan, Q., Zhuo, W., Tang, C.K., et al.: Few-shot object detection with attention-RPN and multi-relation detector. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4013–4022 (2020)
Yadav, A., Vishwakarma, D.K.: Sentiment analysis using deep learning architectures: a review. Artif. Intell. Rev. 53(6), 4335–4385 (2019). https://doi.org/10.1007/s10462-019-09794-5
Wu, M., Parbhoo, S., Hughes, M., et al.: Regional tree regularization for interpretability in deep neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 6413–6421
Kubara, K.J., Manczak, B., Dolicki, B., et al.: Towards transparent and explainable attention models. In: ML Reproducibility Challenge 2020 (2021)
Misheva, B.H., Osterrieder, J., Hirsa, A., et al.: Explainable AI in credit risk management. arXiv preprint arXiv:2103.00949 (2021)
Torrent, N.L., Visani, G., Bagli, E.: PSD2 explainable AI model for credit scoring. arXiv preprint arXiv:2011.10367 (2020)
Loquercio, A., Segu, M., Scaramuzza, D.: A general framework for uncertainty estimation in deep learning. IEEE Robot. Autom. Lett. 5(2), 3153–3160 (2020)
Zhang, Q., Cao, R., Shi, F., et al.: Interpreting CNN knowledge via an explanatory graph. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)
Bau, D., Zhou, B., Khosla, A., et al.: Network dissection: quantifying interpretability of deep visual representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6541–6549 (2017)
Nguyen, A., Clune, J., Bengio, Y., et al.: Plug & play generative networks: conditional iterative generation of images in latent space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4467–4477 (2017)
Bau, D., Zhu, J.Y., Strobelt, H., et al.: Understanding the role of individual units in a deep neural network. Proc. Natl. Acad. Sci. 117(48), 30071–30078 (2020)
Zhou, B., Bau, D., Oliva, A., et al.: Interpreting deep visual representations via network dissection. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2131–2145 (2018)
Fong, R., Vedaldi, A.: Net2Vec: quantifying and explaining how concepts are encoded by filters in deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8730–8738 (2018)
Zhou, B., Khosla, A., Lapedriza, A., et al.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Selvaraju, R.R., Cogswell, M., Das, A., et al.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Wang, H., Wang, Z., Du, M., et al.: Score-CAM: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 24–25 (2020)
Lage, I., Ross, A., Gershman, S.J., et al.: Human-in-the-loop interpretability prior. In: Advances in Neural Information Processing Systems, p. 31 (2018)
Subramanian, A., Pruthi, D., Jhamtani, H., et al.: SPINE: Sparse interpretable neural embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)
Ho, D.: NBDT: neural-backed decision trees. Master’s thesis, EECS Department, University of California, Berkeley (2020)
Nauta, M., van Bree, R., Seifert, C.: Neural prototype trees for interpretable fine-grained image recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14933–14943 (2021)
Fan, F., Wang, G.: Fuzzy logic interpretation of quadratic networks. Neurocomputing 374, 10–21 (2020)
Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: High-precision model-agnostic explanations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)
Zhang, Q., Yang, Y., Ma, H., et al.: Interpreting CNNs via decision trees. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6261–6270 (2019)
Shen, W., Guo, Y., Wang, Y., et al.: Deep differentiable random forests for age estimation. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 404–419 (2019)
Zhang, Q., Wu, Y.N., Zhu, S.C.: Interpretable convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8827–8836 (2018)
Wang, Y., Zhang, X., Hu, X., et al.: Dynamic network pruning with interpretable layerwise channel selection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 6299–6306 (2020)
Luo, J.H., Wu, J., Lin, W.: ThiNet: a filter level pruning method for deep neural network compression. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5058–5066 (2017)
Li, H., Kadav, A., Durdanovic, I., et al.: Pruning filters for efficient ConvNets. arXiv preprint arXiv:1608.08710 (2016)
He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1389–1397 (2017)
Liu, Z., Li, J., Shen, Z., et al.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2736–2744 (2017)
Lin, J., Rao, Y., Lu, J., et al.: Runtime neural pruning. In: Advances in Neural Information Processing Systems 30 (2017)
Gao, X., Zhao, Y., Dudziak, Ł., et al.: Dynamic channel pruning: feature boosting and suppression. arXiv preprint arXiv:1810.05331 (2018)
He, Y., Kang, G., Dong, X., et al.: Soft filter pruning for accelerating deep convolutional neural networks. arXiv preprint arXiv:1808.06866 (2018)
He, Y., Lin, J., Liu, Z., Wang, H., Li, L.-J., Han, S.: AMC: AutoML for model compression and acceleration on mobile devices. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 815–832. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_48
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Si, Y., Cheng, K., Jiang, Z., Zhou, H., Tahir, R. (2022). DRIB: Interpreting DNN with Dynamic Reasoning and Information Bottleneck. In: Wang, Y., Zhu, G., Han, Q., Wang, H., Song, X., Lu, Z. (eds) Data Science. ICPCSEE 2022. Communications in Computer and Information Science, vol 1628. Springer, Singapore. https://doi.org/10.1007/978-981-19-5194-7_14
Download citation
DOI: https://doi.org/10.1007/978-981-19-5194-7_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-5193-0
Online ISBN: 978-981-19-5194-7
eBook Packages: Computer ScienceComputer Science (R0)