10.5555/3491440.3492035guideproceedingsArticle/Chapter ViewAbstractPublication PagesConference Proceedingsacm-pubtype
research-article
Free Access

Disentangled variational autoencoder based multi-label classification with covariance-aware multivariate probit model

Published:07 January 2021Publication History

ABSTRACT

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 important computational sustainability applications as well as on other application domains, using public real-world datasets1. 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.

References

  1. Raed Alazaidah, Fadi Thabtah, and Qasem Al-Radaideh. A multi-label classification approach based on correlations among labels. International Journal of Advanced Computer Science and Applications, 2015.Google ScholarGoogle Scholar
  2. Fernando Benites and Elena Sapozhnikova. Haram: a hierarchical aram neural network for large-scale text classification. In 2015 IEEE International Conference on Data Mining Workshop (ICDMW), pages 847-854. IEEE, 2015.Google ScholarGoogle Scholar
  3. Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, and Prateek Jain. Sparse local embeddings for extreme multi-label classification. In Advances in neural information processing systems, 2015.Google ScholarGoogle Scholar
  4. Wei Bi and James T Kwok. Multilabel classification with label correlations and missing labels. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, pages 1680-1686, 2014.Google ScholarGoogle Scholar
  5. Matthew R Boutell, Jiebo Luo, Xipeng Shen, and Christopher M Brown. Learning multilabel scene classification. Pattern recognition, 37(9):1757- 1771, 2004.Google ScholarGoogle Scholar
  6. James A Carton, Gennady A Chepurin, and Ligang Chen. Soda3: A new ocean climate reanalysis. Journal of Climate, 31(17):6967-6983, 2018.Google ScholarGoogle Scholar
  7. Yao-Nan Chen and Hsuan-Tien Lin. Feature-aware label space dimension reduction for multilabel classification. In Advances in Neural Information Processing Systems, pages 1529-1537, 2012.Google ScholarGoogle Scholar
  8. Di Chen, Yexiang Xue, Daniel Fink, Shuo Chen, and Carla P Gomes. Deep multi-species embedding. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, pages 3639-3646, 2017.Google ScholarGoogle Scholar
  9. Di Chen, Yexiang Xue, and Carla Gomes. End-to-end learning for the deep multivariate probit model. In International Conference on Machine Learning, pages 932-941, 2018.Google ScholarGoogle Scholar
  10. Chen Chen, Haobo Wang, Weiwei Liu, Xingyuan Zhao, Tianlei Hu, and Gang Chen. Twostage label embedding via neural factorization machine for multi-label classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 3304- 3311, 2019.Google ScholarGoogle Scholar
  11. Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, and Yanwen Guo. Multi-label image recognition with graph convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5177-5186, 2019.Google ScholarGoogle Scholar
  12. Tsung-Hsien Chiang, Hung-Yi Lo, and Shou-De Lin. A ranking-based knn approach for multilabel classification. In Asian Conference on Machine Learning, pages 81-96, 2012.Google ScholarGoogle Scholar
  13. Hong-Min Chu, Chih-Kuan Yeh, and Yu-Chiang Frank Wang. Deep generative models for weakly-supervised multi-label classification. In Proceedings of the European Conference on Computer Vision, 2018.Google ScholarGoogle Scholar
  14. Tat-Seng Chua, Jinhui Tang, Richang Hong, Haojie Li, Zhiping Luo, and Yantao Zheng. Nuswide: a real-world web image database from national university of singapore. In Proceedings of the ACM international conference on image and video retrieval, pages 1-9, 2009.Google ScholarGoogle Scholar
  15. Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron C Courville, and Yoshua Bengio. A recurrent latent variable model for sequential data. In Advances in neural information processing systems, pages 2980-2988, 2015.Google ScholarGoogle Scholar
  16. Daniel M Evans, Judy P Che-Castaldo, Deborah Crouse, Frank W Davis, Rebecca Epanchin-Niell, Curtis H Flather, R Kipp Frohlich, Dale D Goble, Ya-Wei Li, and Timothy D Male. Species recovery in the united states: increasing the effectiveness of the endangered species act. Issues in Ecology, 2017.Google ScholarGoogle Scholar
  17. Carla Gomes, Thomas Dietterich, Christopher Barrett, Jon Conrad, Bistra Dilkina, Stefano Ermon, Fei Fang, Andrew Farnsworth, Alan Fern, Xiaoli Fern, et al. Computational sustainability: Computing for a better world and a sustainable future. Communications of the ACM, 62(9):56-65, 2019.Google ScholarGoogle Scholar
  18. Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. β-vae: Learning basic visual concepts with a constrained variational framework. The Eighth International Conference on Learning Representations, 2(5):6, 2017.Google ScholarGoogle Scholar
  19. Mark J. Huiskes and Michael S. Lew. The mir flickr retrieval evaluation. In MIR '08: Proceedings of the 2008 ACM International Conference on Multimedia Information Retrieval, New York, NY, USA, 2008. ACM.Google ScholarGoogle Scholar
  20. Ioannis Katakis, Grigorios Tsoumakas, and Ioannis Vlahavas. Multilabel text classification for automated tag suggestion. Discovery Challenge in Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML-PKDD), page 75, 2008.Google ScholarGoogle Scholar
  21. Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. International conference on learning representation, 2015.Google ScholarGoogle Scholar
  22. Michael Kuhn, Ivica Letunic, Lars Juhl Jensen, and Peer Bork. The sider database of drugs and side effects. Nucleic acids research, 44(D1):D1075- D1079, 2015.Google ScholarGoogle Scholar
  23. Michael Kuhn, Ivica Letunic, Lars Juhl Jensen, and Peer Bork. The sider database of drugs and side effects. Nucleic acids research, 44(D1):D1075- D1079, 2016.Google ScholarGoogle Scholar
  24. Jack Lanchantin, Arshdeep Sekhon, and Yanjun Qi. Neural message passing for multi-label classification. Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2019.Google ScholarGoogle Scholar
  25. James W. Morley, Rebecca L. Selden, Robert J. Latour, Thomas L. Frölicher, Richard J. Seagraves, and Malin L. Pinsky. Projecting shifts in thermal habitat for 686 species on the north american continental shelf. PLOS ONE, 13(5):1-28, 05 2018.Google ScholarGoogle Scholar
  26. M Arthur Munson, Kevin Webb, Daniel Sheldon, Daniel Fink, Wesley M Hochachka, Marshall Iliff, Mirek Riedewald, Daria Sorokina, Brian Sullivan, Christopher Wood, et al. The ebird reference dataset. Cornell Lab of Ornithology and National Audubon Society, 2011.Google ScholarGoogle Scholar
  27. Kenta Nakai and Minoru Kanehisa. A knowledge base for predicting protein localization sites in eukaryotic cells. Genomics, 14(4):897-911, 1992.Google ScholarGoogle Scholar
  28. Jesse Read, Bernhard Pfahringer, Geoff Holmes, and Eibe Frank. Classifier chains for multilabel classification. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 254-269. Springer, 2009.Google ScholarGoogle Scholar
  29. Grigorios Tsoumakas, Ioannis Katakis, and Ioannis Vlahavas. Effective and efficient multilabel classification in domains with large number of labels. In Proceedings of ECML-PKDD 2008 Workshop on Mining Multidimensional Data, pages 53-59, 2008.Google ScholarGoogle Scholar
  30. Sjoerd van Steenkiste, Francesco Locatello, Jürgen Schmidhuber, and Olivier Bachem. Are disentangled representations helpful for abstract visual reasoning? In Advances in Neural Information Processing Systems, pages 14222-14235, 2019.Google ScholarGoogle Scholar
  31. Jiang Wang, Yi Yang, Junhua Mao, Zhiheng Huang, Chang Huang, and Wei Xu. Cnn-rnn: A unified framework for multi-label image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2285-2294, 2016.Google ScholarGoogle Scholar
  32. Baoyuan Wu, Fan Jia, Wei Liu, Bernard Ghanem, and Siwei Lyu. Multi-label learning with missing labels using mixed dependency graphs. International Journal of Computer Vision, 126(8):875-896, 2018.Google ScholarGoogle Scholar
  33. Chih-Kuan Yeh, Wei-Chieh Wu, Wei-Jen Ko, and Yu-Chiang Frank Wang. Learning deep latent space for multi-label classification. In Thirty-First AAAI Conference on Artificial Intelligence, 2017.Google ScholarGoogle Scholar
  34. Hsiang-Fu Yu, Prateek Jain, Purushottam Kar, and Inderjit Dhillon. Large-scale multi-label learning with missing labels. In International conference on machine learning, pages 593-601, 2014.Google ScholarGoogle Scholar
  35. Yu Zhang and Dit-Yan Yeung. Multilabel relationship learning. ACM Transactions on Knowledge Discovery from Data (TKDD), 7(2):7, 2013.Google ScholarGoogle Scholar
  36. Min-Ling Zhang and Zhi-Hua Zhou. Ml-knn: A lazy learning approach to multilabel learning. Pattern recognition, 40(7):2038-2048, 2007.Google ScholarGoogle Scholar
  37. Min-Ling Zhang and Zhi-Hua Zhou. A review on multi-label learning algorithms. IEEE transactions on knowledge and data engineering, 26(8):1819-1837, 2013.Google ScholarGoogle Scholar
  38. Min-Ling Zhang, Yu-Kun Li, Xu-Ying Liu, and Xin Geng. Binary relevance for multilabel learning: an overview. Frontiers of Computer Science, 12(2):191-202, 2018.Google ScholarGoogle Scholar

Index Terms

(auto-classified)
  1. Disentangled variational autoencoder based multi-label classification with covariance-aware multivariate probit model

          Comments

          Login options

          Check if you have access through your login credentials or your institution to get full access on this article.

          Sign in
          • Published in

            cover image Guide Proceedings
            IJCAI'20: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
            January 2021
            5311 pages
            ISBN:9780999241165

            Copyright © 2020 International Joint Conferences on Artificial Intelligence

            Publisher

            Unknown publishers

            Publication History

            • Published: 7 January 2021

            Qualifiers

            • research-article
            • Research
            • Refereed limited
          • Article Metrics

            • Downloads (Last 12 months)17
            • Downloads (Last 6 weeks)2

            Other Metrics

          PDF Format

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader
          About Cookies On This Site

          We use cookies to ensure that we give you the best experience on our website.

          Learn more

          Got it!