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
D. Angluin, P. Laird, Learning from noisy examples. Mach. Learn. 2(4), 343–370 (1988)
D. Arpit et al., A closer look at memorization in deep networks, in International Conference on Machine Learning, PMLR (2017), pp. 233–242
M. Belkin, P. Niyogi, V. Sindhwani, Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 7, 2399–2434 (2006)
D.M. Blei, A. Kucukelbir, J.D. McAuliffe, Variational inference: a review for statisticians. J. Am. Statist. Assoc. 112(518), 859–877 (2017)
H. Cheng et al., Learning with instance-dependent label noise: a sample sieve approach, in ICLR (2021)
J. Cheng et al., Learning with bounded instance and label-dependent label noise, in ICML (2020)
B. Han et al., Co-teaching: robust training of deep neural networks with extremely noisy labels, in NeurIPS (2018), pp. 8527–8537
L. Jiang et al., MentorNet: learning data-driven curriculum for very deep neural networks on corrupted labels, in ICML (2018), pp. 2309–2318
D.P. Kingma, M. Welling, Auto-encoding variational bayes (2013). arXiv preprint arXiv:1312.6114
A. Krizhevsky, Learning multiple layers of features from tiny images. Technical report, 2009
A. Kuznetsova et al., The open images dataset v4. Int. J. Comput. Vis. 128(7), 1956–1981 (2020)
W. Li et al., Webvision database: visual learning and understanding from web data (2017). arXiv preprint arXiv:1708.02862
X. Li et al., Provably end-to-end label-noise learning without anchor points, in ICML (2021)
T. Liu, D. Tao, Classification with noisy labels by importance reweighting. IEEE Trans. Pattern Anal. Mach. Intell. 38(3), 447–461 (2016)
Y. Liu, The importance of understanding instance-level noisy labels, in ICML (2021)
D. Mahajan et al., Exploring the limits of weakly supervised pretraining, in Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 181–196
E. Malach, S. Shalev-Shwartz, Decoupling when to update from how to update, in NeurIPS (2017), pp. 960–970
N. Natarajan et al., Learning with noisy labels, in NeurIPS (2013), pp. 1196–1204
Y. Netzer et al., Reading digits in natural images with unsupervised feature learning, in NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011)
G. Patrini et al., Making deep neural networks robust to label noise: a loss correction approach, in CVPR (2017), pp. 1944–1952
J. Pearl, Causality (Cambridge University Press, Cambridge, 2009)
J. Peters, D. Janzing, B. Schölkopf, Elements of Causal Inference: Foundations and learning Algorithms (The MIT Press, Cambridge, MA, 2017)
B. Schölkopf et al., On causal and anticausal learning, in 29th International Conference on Machine Learning (ICML 2012) (International Machine Learning Society, 2012), pp. 1255–12620
C. Scott, A rate of convergence for mixture proportion estimation, with application to learning from noisy labels, in AISTATS (2015), pp. 838–846
P. Spirtes, K. Zhang, Causal discovery and inference: concepts and recent methodological advances, in Applied Informatics, vol. 3 (Springer. 2016), p. 3
P. Spirtes et al., Causation, Prediction, and Search (The MIT Press, Cambridge, MA, 2000)
X. Xia et al., Are anchor points really indispensable in label-noise learning?, in NeurIPS (2019), pp. 6835–6846
X. Xia et al., Are anchor points really indispensable in label-noise Learning?, in: NeurIPS (2019), pp. 6838–6849
X. Xia et al., Part-dependent label noise: towards instance-dependent label noise, in NeurIPS (2020)
H. Xiao, K. Rasul, R. Vollgraf, Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017). arXiv preprint arXiv:1708.07747
T. Xiao et al., Learning from massive noisy labeled data for image classification, in CVPR (2015), pp. 2691–2699
Q. Yao et al., Searching to exploit memorization effect in learning with noisy labels, in ICML (2020)
Y. Yao et al., Dual T: reducing estimation error for transition matrix in label-noise learning, in NeurIPS (2020)
Y. Yao et al., Instance-dependent label-noise learning under a structural causal model, Advances in Neural Information Processing Systems,34, 4409–4420 (2021)
H. Zhang et al., Mixup: beyond empirical risk minimization, in ICLR’18 (2018)
Z. Zhu, T. Liu, Y. Liu, A second-order approach to learning with instance-dependent label noise, in CVPR (2021)
Z. Zhu, Y. Song, Y. Liu, Clusterability as an alternative to anchor points when learning with noisy labels (2021). arXiv preprint arXiv:2102.05291
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Yao, Y., Liu, T., Gong, M., Han, B., Niu, G., Zhang, K. (2023). Causality Encourages the Identifiability of Instance-Dependent Label Noise. In: Li, S., Chu, Z. (eds) Machine Learning for Causal Inference. Springer, Cham. https://doi.org/10.1007/978-3-031-35051-1_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-35051-1_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35050-4
Online ISBN: 978-3-031-35051-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)