Skip to main content

Semantic Attribution for Explainable Uncertainty Quantification

  • Conference paper
  • First Online:
Epistemic Uncertainty in Artificial Intelligence (Epi UAI 2023)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14523))

  • 53 Accesses

Abstract

Bayesian deep learning, with an emphasis on uncertainty quantification, is receiving growing interest in building reliable models. Nonetheless, interpreting and explaining the origins and reasons for uncertainty presents a significant challenge. In this paper, we present semantic uncertainty attribution as a tool for pinpointing the primary factors contributing to uncertainty. This approach allows us to explain why a particular image carries high uncertainty, thereby making our models more interpretable. Specifically, we utilize the variational autoencoder to disentangle different semantic factors within the latent space and link the uncertainty to corresponding semantic factors for an explanation. The proposed techniques can also enhance explainable out-of-distribution (OOD) detection. We can not only identify OOD samples via their uncertainty, but also provide reasoning rooted in a semantic concept.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    There is debate over whether deep ensemble is a Bayesian method. We believe it is since each ensemble component can serve as a mode of \(p(\theta |\mathcal {D})\).

References

  1. Antorán, J., Bhatt, U., Adel, T., Weller, A., Hernández-Lobato, J.M.: Getting a clue: A method for explaining uncertainty estimates. arXiv preprint: arXiv:2006.06848 (2020)

  2. Chen, R.T., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. In: Advances in Neural Information Processing Systems, vol. 31 (2018)

    Google Scholar 

  3. Dabkowski, P., Gal, Y.: Real time image saliency for black box classifiers. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  4. Depeweg, S., Hernandez-Lobato, J.M., Doshi-Velez, F., Udluft, S.: Decomposition of uncertainty in bayesian deep learning for efficient and risk-sensitive learning. In: International Conference on Machine Learning, pp. 1184–1193. PMLR (2018)

    Google Scholar 

  5. Fong, R., Patrick, M., Vedaldi, A.: Understanding deep networks via extremal perturbations and smooth masks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2950–2958 (2019)

    Google Scholar 

  6. Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3429–3437 (2017)

    Google Scholar 

  7. Higgins, I., et al.: beta-VAE: learning basic visual concepts with a constrained variational framework (2016)

    Google Scholar 

  8. Kapishnikov, A., Venugopalan, S., Avci, B., Wedin, B., Terry, M., Bolukbasi, T.: Guided integrated gradients: an adaptive path method for removing noise. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5050–5058 (2021)

    Google Scholar 

  9. Kulkarni, T.D., Whitney, W.F., Kohli, P., Tenenbaum, J.: Deep convolutional inverse graphics network. In: Advances in Neural Information Processing Systems, vol. 28 (2015)

    Google Scholar 

  10. Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles (2016). http://arxiv.org/abs/1612.01474

  11. Ley, D., Bhatt, U., Weller, A.: \(\{\)\(\backslash \)delta\(\}\)-clue: diverse sets of explanations for uncertainty estimates. arXiv preprint: arXiv:2104.06323 (2021)

  12. Ley, D., Bhatt, U., Weller, A.: Diverse, global and amortised counterfactual explanations for uncertainty estimates. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 7390–7398 (2022)

    Google Scholar 

  13. Margonis, V., Davvetas, A., Klampanos, I.A.: Wela-VAE: learning alternative disentangled representations using weak labels. arXiv preprint: arXiv:2008.09879 (2020)

  14. Perez, I., Skalski, P., Barns-Graham, A., Wong, J., Sutton, D.: Attribution of predictive uncertainties in classification models. In: The 38th Conference on Uncertainty in Artificial Intelligence (2022)

    Google Scholar 

  15. Petsiuk, V., Das, A., Saenko, K.: Rise: Randomized input sampling for explanation of black-box models. arXiv preprint: arXiv:1806.07421 (2018)

  16. Rey, L.A.P., İşler, B., Holenderski, M., Jarnikov, D.: Identifying the sources of uncertainty in object classification (2020)

    Google Scholar 

  17. Ribeiro, M.T., Singh, S., Guestrin, C.: " why should i trust you?" explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)

    Google Scholar 

  18. Sarhan, M.H., Eslami, A., Navab, N., Albarqouni, S.: Learning interpretable disentangled representations using adversarial VAEs. In: Wang, Q., et al. (eds.) Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data. Lecture Notes in Computer Science(), vol. 11795, pp. 37–44. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-33391-1_5

    Chapter  Google Scholar 

  19. 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: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)

    Google Scholar 

  20. Shrikumar, A., Greenside, P., Shcherbina, A., Kundaje, A.: Not just a black box: learning important features through propagating activation differences. arXiv preprint: arXiv:1605.01713 (2016)

  21. Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint: arXiv:1312.6034 (2013)

  22. Smilkov, D., Thorat, N., Kim, B., Viégas, F., Wattenberg, M.: SmoothGrad: removing noise by adding noise. arXiv preprint: arXiv:1706.03825 (2017)

  23. Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319–3328. PMLR (2017)

    Google Scholar 

  24. Wang, H., Joshi, D., Wang, S., Ji, Q.: Gradient-based uncertainty attribution for explainable Bayesian deep learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12044–12053 (2023)

    Google Scholar 

  25. Xu, S., Venugopalan, S., Sundararajan, M.: Attribution in scale and space. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9680–9689 (2020)

    Google Scholar 

  26. Yang, Q., Zhu, X., Fwu, J.K., Ye, Y., You, G., Zhu, Y.: MFPP: morphological fragmental perturbation pyramid for black-box model explanations. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 1376–1383. IEEE (2021)

    Google Scholar 

  27. Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision - ECCV 2014. Lecture Notes in Computer Science, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Hanjing Wang .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wang, H., Wang, S., Ji, Q. (2024). Semantic Attribution for Explainable Uncertainty Quantification. In: Cuzzolin, F., Sultana, M. (eds) Epistemic Uncertainty in Artificial Intelligence . Epi UAI 2023. Lecture Notes in Computer Science(), vol 14523. Springer, Cham. https://doi.org/10.1007/978-3-031-57963-9_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-57963-9_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-57962-2

  • Online ISBN: 978-3-031-57963-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics