LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labels

In real-world applications, perfect labels are rarely available, making it challenging to develop robust machine learning algorithms that can handle noisy labels. Recent methods have focused on filtering noise based on the discrepancy between model predictions and given noisy labels, assuming that samples with small classification losses are clean. This work takes a different approach by leveraging the consistency between the learned model and the entire noisy dataset using the rich representational and topological information in the data. We introduce LaplaceConfidence, a method that to obtain label confidence (i.e., clean probabilities) utilizing the Laplacian energy. Specifically, it first constructs graphs based on the feature representations of all noisy samples and minimizes the Laplacian energy to produce a low-energy graph. Clean labels should fit well into the low-energy graph while noisy ones should not, allowing our method to determine data's clean probabilities. Furthermore, LaplaceConfidence is embedded into a holistic method for robust training, where co-training technique generates unbiased label confidence and label refurbishment technique better utilizes it. We also explore the dimensionality reduction technique to accommodate our method on large-scale noisy datasets. Our experiments demonstrate that LaplaceConfidence outperforms state-of-the-art methods on benchmark datasets under both synthetic and real-world noise.

[1]  C. Schmid,et al.  Learning with Neighbor Consistency for Noisy Labels , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Zhi-Fan Wu,et al.  NGC: A Unified Framework for Learning with Open-World Noisy Data , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Shyamgopal Karthik,et al.  Learning From Long-Tailed Data With Noisy Labels , 2021, ArXiv.

[4]  Yi Ding,et al.  Augmentation Strategies for Learning with Noisy Labels , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Se-Young Yun,et al.  FINE Samples for Learning with Noisy Labels , 2021, NeurIPS.

[6]  Dimitris N. Metaxas,et al.  A Topological Filter for Learning with Label Noise , 2020, NeurIPS.

[7]  N. O'Connor,et al.  Multi-Objective Interpolation Training for Robustness to Label Noise , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Ivor W. Tsang,et al.  A Survey of Label-noise Representation Learning: Past, Present and Future , 2020, ArXiv.

[9]  Hwanjun Song,et al.  Learning From Noisy Labels With Deep Neural Networks: A Survey , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Luc Van Gool,et al.  Learning To Classify Images Without Labels , 2020, ECCV.

[11]  Maya R. Gupta,et al.  Deep k-NN for Noisy Labels , 2020, ICML.

[12]  Ce Liu,et al.  Supervised Contrastive Learning , 2020, NeurIPS.

[13]  Junnan Li,et al.  DivideMix: Learning with Noisy Labels as Semi-supervised Learning , 2020, ICLR.

[14]  David Berthelot,et al.  FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence , 2020, NeurIPS.

[15]  Quoc V. Le,et al.  Randaugment: Practical automated data augmentation with a reduced search space , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[16]  Junmo Kim,et al.  NLNL: Negative Learning for Noisy Labels , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[17]  Noel E. O'Connor,et al.  Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning , 2019, 2020 International Joint Conference on Neural Networks (IJCNN).

[18]  Quoc V. Le,et al.  AutoAugment: Learning Augmentation Strategies From Data , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Yueming Lyu,et al.  Curriculum Loss: Robust Learning and Generalization against Label Corruption , 2019, ICLR.

[20]  Jae-Gil Lee,et al.  SELFIE: Refurbishing Unclean Samples for Robust Deep Learning , 2019, ICML.

[21]  Pengfei Chen,et al.  Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels , 2019, ICML.

[22]  David Berthelot,et al.  MixMatch: A Holistic Approach to Semi-Supervised Learning , 2019, NeurIPS.

[23]  Noel E. O'Connor,et al.  Unsupervised label noise modeling and loss correction , 2019, ICML.

[24]  Kun Yi,et al.  Probabilistic End-To-End Noise Correction for Learning With Noisy Labels , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Xingrui Yu,et al.  How does Disagreement Help Generalization against Label Corruption? , 2019, ICML.

[26]  Mohan S. Kankanhalli,et al.  Learning to Learn From Noisy Labeled Data , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Yanyao Shen,et al.  Learning with Bad Training Data via Iterative Trimmed Loss Minimization , 2018, ICML.

[28]  James Bailey,et al.  Dimensionality-Driven Learning with Noisy Labels , 2018, ICML.

[29]  Brendan van Rooyen,et al.  Learning from binary labels with instance-dependent noise , 2018, Machine Learning.

[30]  Masashi Sugiyama,et al.  Co-teaching: Robust training of deep neural networks with extremely noisy labels , 2018, NeurIPS.

[31]  Le Song,et al.  Iterative Learning with Open-set Noisy Labels , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[32]  Kiyoharu Aizawa,et al.  Joint Optimization Framework for Learning with Noisy Labels , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[33]  Li Fei-Fei,et al.  MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels , 2017, ICML.

[34]  Lei Zhang,et al.  CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[35]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

[36]  Michael E. Houle,et al.  Local Intrinsic Dimensionality I: An Extreme-Value-Theoretic Foundation for Similarity Applications , 2017, SISAP.

[37]  Kotagiri Ramamohanarao,et al.  Learning with Bounded Instance- and Label-dependent Label Noise , 2017, ICML.

[38]  Wei Li,et al.  WebVision Database: Visual Learning and Understanding from Web Data , 2017, ArXiv.

[39]  Yoshua Bengio,et al.  A Closer Look at Memorization in Deep Networks , 2017, ICML.

[40]  Harri Valpola,et al.  Weight-averaged consistency targets improve semi-supervised deep learning results , 2017, ArXiv.

[41]  Geoffrey E. Hinton,et al.  Regularizing Neural Networks by Penalizing Confident Output Distributions , 2017, ICLR.

[42]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[43]  Richard Nock,et al.  Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[45]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[46]  Xinlei Chen,et al.  Webly Supervised Learning of Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[47]  Dumitru Erhan,et al.  Training Deep Neural Networks on Noisy Labels with Bootstrapping , 2014, ICLR.

[48]  D. Tao,et al.  Classification with Noisy Labels by Importance Reweighting , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[49]  Joan Bruna,et al.  Training Convolutional Networks with Noisy Labels , 2014, ICLR 2014.

[50]  Mark Newman,et al.  Detecting community structure in networks , 2004 .

[51]  Zoubin Ghahramani,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[52]  Angelica I. Avilés-Rivero,et al.  LaplaceNet: A Hybrid Energy-Neural Model for Deep Semi-Supervised Classification , 2021, ArXiv.

[53]  Zhi-Hua Zhou,et al.  A brief introduction to weakly supervised learning , 2018 .

[54]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .