Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Model

Multi-label classification is the challenging task of predicting the presence and absence of multiple targets, involving representation learning and label correlation modeling. We propose a novel framework for multi-label classification, Multivariate Probit Variational AutoEncoder (MPVAE), that effectively learns latent embedding spaces as well as label correlations. MPVAE learns and aligns two probabilistic embedding spaces for labels and features respectively. The decoder of MPVAE takes in the samples from the embedding spaces and models the joint distribution of output targets under a Multivariate Probit model by learning a shared covariance matrix. We show that MPVAE outperforms the existing state-of-the-art methods on a variety of application domains, using public real-world datasets. MPVAE is further shown to remain robust under noisy settings. Lastly, we demonstrate the interpretability of the learned covariance by a case study on a bird observation dataset.

[1]  Sjoerd van Steenkiste,et al.  Are Disentangled Representations Helpful for Abstract Visual Reasoning? , 2019, NeurIPS.

[2]  Yexiang Xue,et al.  Deep Multi-species Embedding , 2016, IJCAI.

[3]  Wei Liu,et al.  Multi-label Learning with Missing Labels Using Mixed Dependency Graphs , 2018, International Journal of Computer Vision.

[4]  Chao-Kai Chiang,et al.  Asian Conference on Machine Learning , 2014 .

[5]  Fernando Benites,et al.  HARAM: A Hierarchical ARAM Neural Network for Large-Scale Text Classification , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[6]  R. Quatrano.  Genomics , 1998, Plant Cell.

[7]  Di Chen,et al.  End-to-End Learning for the Deep Multivariate Probit Model , 2018, ICML.

[8]  Yoshua Bengio,et al.  A Recurrent Latent Variable Model for Sequential Data , 2015, NIPS.

[9]  Byron K. Williams,et al.  Species recovery in the united states: Increasing the effectiveness of the endangered species act , 2016 .

[10]  Arshdeep Sekhon,et al.  Neural Message Passing for Multi-Label Classification , 2019, ECML/PKDD.

[11]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[12]  Dit-Yan Yeung,et al.  Multilabel relationship learning , 2013, TKDD.

[13]  Xin Geng,et al.  Binary relevance for multi-label learning: an overview , 2018, Frontiers of Computer Science.

[14]  Prateek Jain,et al.  Sparse Local Embeddings for Extreme Multi-label Classification , 2015, NIPS.

[15]  Qasem A. Al-Radaideh,et al.  A Multi-Label Classification Approach Based on Correlations Among Labels , 2015 .

[16]  Xiu-Shen Wei,et al.  Multi-Label Image Recognition With Graph Convolutional Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Rynson W. H. Lau,et al.  Knowledge and Data Engineering for e-Learning Special Issue of IEEE Transactions on Knowledge and Data Engineering , 2008 .

[18]  Peer Bork,et al.  The SIDER database of drugs and side effects , 2015, Nucleic Acids Res..

[19]  M. Kanehisa,et al.  A knowledge base for predicting protein localization sites in eukaryotic cells , 1992, Genomics.

[20]  Yu-Chiang Frank Wang,et al.  Deep Generative Models for Weakly-Supervised Multi-Label Classification , 2018, ECCV.

[21]  Wei Xu,et al.  CNN-RNN: A Unified Framework for Multi-label Image Classification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Jiebo Luo,et al.  Learning multi-label scene classification , 2004, Pattern Recognit..

[23]  Min-Ling Zhang,et al.  A Review on Multi-Label Learning Algorithms , 2014, IEEE Transactions on Knowledge and Data Engineering.

[24]  G. Hong,et al.  Nucleic Acids Research , 2015, Nucleic Acids Research.

[25]  Grigorios Tsoumakas,et al.  Multilabel Text Classification for Automated Tag Suggestion , 2008 .

[26]  Hsuan-Tien Lin,et al.  Feature-aware Label Space Dimension Reduction for Multi-label Classification , 2012, NIPS.

[27]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[28]  Rebecca L. Selden,et al.  Projecting shifts in thermal habitat for 686 species on the North American continental shelf , 2018, PloS one.

[29]  James T. Kwok,et al.  Multilabel Classification with Label Correlations and Missing Labels , 2014, AAAI.

[30]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[31]  James A. Carton,et al.  SODA3: A New Ocean Climate Reanalysis , 2018, Journal of Climate.

[32]  Weiwei Liu,et al.  Two-Stage Label Embedding via Neural Factorization Machine for Multi-Label Classification , 2019, AAAI.

[33]  Joseph Y. Halpern,et al.  Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence , 2014, AAAI 2014.

[34]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[35]  Inderjit S. Dhillon,et al.  Large-scale Multi-label Learning with Missing Labels , 2013, ICML.

[36]  Geoff Holmes,et al.  Classifier chains for multi-label classification , 2009, Machine Learning.

[37]  Yu-Chiang Frank Wang,et al.  Learning Deep Latent Spaces for Multi-Label Classification , 2017, ArXiv.

[38]  Zhi-Hua Zhou,et al.  ML-KNN: A lazy learning approach to multi-label learning , 2007, Pattern Recognit..

[39]  Grigorios Tsoumakas,et al.  Effective and Efficient Multilabel Classification in Domains with Large Number of Labels , 2008 .