Noise-robust classification with hypergraph neural network

This paper presents a novel version of hypergraph neural network method. This method is utilized to solve the noisy label learning problem. First, we apply the PCA dimensional reduction technique to the feature matrices of the image datasets in order to reduce the “noise” and the redundant features in the feature matrices of the image datasets and to reduce the runtime constructing the hypergraph of the hypergraph neural network method. Then, the classic graph based semisupervised learning method, the classic hypergraph based semi-supervised learning method, the graph neural network, the hypergraph neural network, and our proposed hypergraph neural network are employed to solve the noisy label learning problem. The accuracies of these five methods are evaluated and compared. Experimental results show that the hypergraph neural network methods achieve the best performance when the noise level increases. Moreover, the hypergraph neural network methods are at least as good as the graph neural network.

[1]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[2]  Song Bai,et al.  Hypergraph Convolution and Hypergraph Attention , 2019, Pattern Recognit..

[3]  Ata Kabán,et al.  Label-Noise Robust Logistic Regression and Its Applications , 2012, ECML/PKDD.

[4]  Bernhard Schölkopf,et al.  Beyond pairwise classification and clustering using hypergraphs , 2005, NIPS 2005.

[5]  Xin Geng,et al.  Label Distribution Learning , 2013, 2013 IEEE 13th International Conference on Data Mining Workshops.

[6]  Zijin Zhao,et al.  Classification in the presence of heavy label noise: A Markov chain sampling framework , 2017 .

[7]  Aritra Ghosh,et al.  Robust Loss Functions under Label Noise for Deep Neural Networks , 2017, AAAI.

[8]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[9]  Bernhard Schölkopf,et al.  Learning with Hypergraphs: Clustering, Classification, and Embedding , 2006, NIPS.

[10]  Jacob Goldberger,et al.  A deep neural network witharestricted noisy channel for identification of functional introns , 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

[11]  Ryan A. Rossi,et al.  Deep Feature Learning for Graphs , 2017, ArXiv.

[12]  Kai Zhao,et al.  Label Distribution Learning Forests , 2017, NIPS.

[13]  Bin Luo,et al.  Semi-Supervised Learning With Graph Learning-Convolutional Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Zhiwu Lu,et al.  Noise-robust semi-supervised learning via fast sparse coding , 2015, Pattern Recognit..

[15]  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).

[16]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[17]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[18]  Jacob Goldberger,et al.  Training deep neural-networks based on unreliable labels , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[19]  Mert R. Sabuncu,et al.  Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels , 2018, NeurIPS.

[20]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[21]  Stephan Günnemann,et al.  Predict then Propagate: Graph Neural Networks meet Personalized PageRank , 2018, ICLR.

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

[23]  Jacob Goldberger,et al.  Training deep neural-networks using a noise adaptation layer , 2016, ICLR.

[24]  M. Verleysen,et al.  Classification in the Presence of Label Noise: A Survey , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Qingshan Liu,et al.  Image retrieval via probabilistic hypergraph ranking , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  Jakramate Bootkrajang,et al.  Supervised learning with random labelling errors , 2013 .

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

[28]  Yue Gao,et al.  Hypergraph Neural Networks , 2018, AAAI.