PK-GCN: Prior Knowledge Assisted Image Classification using Graph Convolution Networks

Deep learning has gained great success in various classification tasks. Typically, deep learning models learn underlying features directly from data, and no underlying relationship between classes are included. Similarity between classes can influence the performance of classification. In this article, we propose a method that incorporates class similarity knowledge into convolutional neural networks models using a graph convolution layer. We evaluate our method on two benchmark image datasets: MNIST and CIFAR10, and analyze the results on different data and model sizes. Experimental results show that our model can improve classification accuracy, especially when the amount of available data is small.

[1]  Steven R. Young,et al.  Optimizing deep learning hyper-parameters through an evolutionary algorithm , 2015, MLHPC@SC.

[2]  Masanori Suganuma,et al.  A genetic programming approach to designing convolutional neural network architectures , 2017, GECCO.

[3]  Eunho Yang,et al.  DropMax: Adaptive Variational Softmax , 2017, NeurIPS.

[4]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

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

[6]  Yi Pan,et al.  A Parallel Matrix-Based Method for Computing Approximations in Incomplete Information Systems , 2015, IEEE Transactions on Knowledge and Data Engineering.

[7]  Yi Pan,et al.  An adaptive genetic fuzzy multi-path routing protocol for wireless ad-hoc networks , 2005, Sixth International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing and First ACIS International Workshop on Self-Assembling Wireless Network.

[8]  Ralph Roskies,et al.  Bridges: a uniquely flexible HPC resource for new communities and data analytics , 2015, XSEDE.

[9]  Alejandro Baldominos Gómez,et al.  Evolutionary convolutional neural networks: An application to handwriting recognition , 2017, Neurocomputing.

[10]  Eric P. Xing,et al.  Harnessing Deep Neural Networks with Logic Rules , 2016, ACL.

[11]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[12]  Lior Rokach,et al.  Ensemble learning: A survey , 2018, WIREs Data Mining Knowl. Discov..

[13]  Stefano Ermon,et al.  Label-Free Supervision of Neural Networks with Physics and Domain Knowledge , 2016, AAAI.

[14]  Yun Zhu,et al.  Efficient parallel boolean matrix based algorithms for computing composite rough set approximations , 2016, Inf. Sci..

[15]  Marco Gori,et al.  Integrating Prior Knowledge into Deep Learning , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[16]  Liang Lin,et al.  Hybrid Knowledge Routed Modules for Large-scale Object Detection , 2018, NeurIPS.

[17]  Yi Pan,et al.  Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm , 2020, ArXiv.

[18]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[19]  Kristen Grauman,et al.  Semantic Kernel Forests from Multiple Taxonomies , 2012, NIPS.

[20]  Bing Wang,et al.  Prior knowledge-based deep learning method for indoor object recognition and application , 2018 .

[21]  Hiroshi Inoue,et al.  Data Augmentation by Pairing Samples for Images Classification , 2018, ArXiv.

[22]  Yi Pan,et al.  Gradient Amplification: An efficient way to train deep neural networks , 2020, Big Data Min. Anal..

[23]  Noah A. Smith,et al.  Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2016, ACL 2016.

[24]  Yi Pan,et al.  Deep Fuzzy Neural Networks for Biomarker Selection for Accurate Cancer Detection , 2020, IEEE Transactions on Fuzzy Systems.

[25]  Samy Bengio,et al.  Large-Scale Object Classification Using Label Relation Graphs , 2014, ECCV.

[26]  Nancy Wilkins-Diehr,et al.  XSEDE: Accelerating Scientific Discovery , 2014, Computing in Science & Engineering.

[27]  Min Li,et al.  DeepEP: a deep learning framework for identifying essential proteins , 2019, BMC Bioinformatics.

[28]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[29]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[30]  Quoc V. Le,et al.  Large-Scale Evolution of Image Classifiers , 2017, ICML.

[31]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[33]  Yohei Kikuta,et al.  ClassSim: Similarity between Classes Defined by Misclassification Ratios of Trained Classifiers , 2018, ArXiv.

[34]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[35]  Yi Pan,et al.  TW-Co-MFC: Two-level weighted collaborative fuzzy clustering based on maximum entropy for multi-view data , 2021, Tsinghua Science and Technology.

[36]  Guy Van den Broeck,et al.  A Semantic Loss Function for Deep Learning with Symbolic Knowledge , 2017, ICML.

[37]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[38]  Kyunghyun Cho,et al.  Graph Convolutional Networks for Classification with a Structured Label Space , 2017, ArXiv.

[39]  Yi Pan,et al.  International Journal of Approximate Reasoning a Comparison of Parallel Large-scale Knowledge Acquisition Using Rough Set Theory on Different Mapreduce Runtime Systems , 2022 .

[40]  Jude W. Shavlik,et al.  Knowledge-Based Artificial Neural Networks , 1994, Artif. Intell..

[41]  Ramesh Raskar,et al.  Designing Neural Network Architectures using Reinforcement Learning , 2016, ICLR.

[42]  Takashi Matsubara,et al.  Data Augmentation Using Random Image Cropping and Patching for Deep CNNs , 2018, IEEE Transactions on Circuits and Systems for Video Technology.