{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T14:59:32Z","timestamp":1717599572411},"reference-count":40,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,3,1]]},"DOI":"10.1587\/transinf.2021edp7161","type":"journal-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T22:25:06Z","timestamp":1646087106000},"page":"667-678","source":"Crossref","is-referenced-by-count":1,"title":["Latent Space Virtual Adversarial Training for Supervised and Semi-Supervised Learning"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Genki","family":"OSADA","sequence":"first","affiliation":[{"name":"Philips Co-Creation Center"},{"name":"University of Tsukuba"},{"name":"I Dragon Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Budrul","family":"AHSAN","sequence":"additional","affiliation":[{"name":"Philips Co-Creation Center"},{"name":"The Tokyo Foundation for Policy Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Revoti","family":"PRASAD BORA","sequence":"additional","affiliation":[{"name":"Lowe's Services India Pvt. Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"NISHIDE","sequence":"additional","affiliation":[{"name":"University of Tsukuba"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] G. Osada, B. Ahsan, R.P. Bora, and T. Nishide, \u201cRegularization with latent space virtual adversarial training,\u201d European Conference on Computer Vision (ECCV), vol.12346, pp.565-581, 2020. 10.1007\/978-3-030-58452-8_33","DOI":"10.1007\/978-3-030-58452-8_33"},{"key":"2","unstructured":"[2] T. Miyato, S.I. Maeda, M. Koyama, K. Nakae, and S. Ishii, \u201cDistributional smoothing with virtual adversarial training,\u201d International Conference on Learning Representations, 2016."},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] T. Miyato, S.-I. Maeda, M. Koyama, and S. Ishii, \u201cVirtual adversarial training: a regularization method for supervised and semi-supervised learning,\u201d IEEE transactions on pattern analysis and machine intelligence, vol.41, no.8, pp.1979-1993, 2018. 10.1109\/tpami.2018.2858821","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"4","unstructured":"[4] D.P. Kingma and M. Welling, \u201cAuto-encoding variational bayes,\u201d International Conference on Learning Representations, 2014."},{"key":"5","unstructured":"[5] D.P. Kingma and P. Dhariwal, \u201cGlow: Generative flow with invertible 1x1 convolutions,\u201d Advances in Neural Information Processing Systems 31, ed. S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, pp.10215-10224, Curran Associates, Inc., 2018."},{"key":"6","unstructured":"[6] D. Zhou, O. Bousquet, T.N. Lal, J. Weston, and B. Sch\u00f6lkopf, \u201cLearning with local and global consistency,\u201d Advances in Neural Information Processing Systems 16, ed. S. Thrun, L.K. Saul, and B. Sch\u00f6lkopf, pp.321-328, MIT Press, 2004."},{"key":"7","unstructured":"[7] S. Laine and T. Aila, \u201cTemporal ensembling for semi-supervised learning,\u201d International Conference on Learning Representations, 2017."},{"key":"8","unstructured":"[8] A. Tarvainen and H. Valpola, \u201cMean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results,\u201d Advances in Neural Information Processing Systems 30, ed. I. Guyon, U.V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, pp.1195-1204, Curran Associates, Inc., 2017."},{"key":"9","unstructured":"[9] M. Sajjadi, M. Javanmardi, and T. Tasdizen, \u201cRegularization with stochastic transformations and perturbations for deep semi-supervised learning,\u201d Advances in Neural Information Processing Systems 29, ed. D.D. Lee, M. Sugiyama, U.V. Luxburg, I. Guyon, and R. Garnett, pp.1163-1171, Curran Associates, Inc., 2016."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] S. Park, J. Park, S.J. Shin, and I.C. Moon, \u201cAdversarial dropout for supervised and semi-supervised learning,\u201d Thirty-Second AAAI Conference on Artificial Intelligence, 2018.","DOI":"10.1609\/aaai.v32i1.11634"},{"key":"11","unstructured":"[11] B. Athiwaratkun, M. Finzi, P. Izmailov, and A.G. Wilson, \u201cThere are many consistent explanations of unlabeled data: Why you should average,\u201d International Conference on Learning Representations, 2019."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] V. Verma, A. Lamb, J. Kannala, Y. Bengio, and D. Lopez-Paz, \u201cInterpolation consistency training for semi-supervised learning,\u201d Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pp.3635-3641, International Joint Conferences on Artificial Intelligence Organization, 7 2019. 10.24963\/ijcai.2019\/504","DOI":"10.24963\/ijcai.2019\/504"},{"key":"13","unstructured":"[13] D. Berthelot, N. Carlini, I. Goodfellow, N. Papernot, A. Oliver, and C.A. Raffel, \u201cMixmatch: A holistic approach to semi-supervised learning,\u201d Advances in Neural Information Processing Systems 32, ed. H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett, pp.5049-5059, Curran Associates, Inc., 2019."},{"key":"14","unstructured":"[14] Q. Xie, Z. Dai, E. Hovy, M.T. Luong, and Q.V. Le, \u201cUnsupervised data augmentation for consistency training,\u201d 2019."},{"key":"15","unstructured":"[15] K. Kamnitsas, D. Castro, L.L. Folgoc, I. Walker, R. Tanno, D. Rueckert, B. Glocker, A. Criminisi, and A. Nori, \u201cSemi-supervised learning via compact latent space clustering,\u201d Proceedings of the 35th International Conference on Machine Learning, ed. J. Dy and A. Krause, Proceedings of Machine Learning Research, vol.80, Stockholmsm\u00e4ssan, Stockholm Sweden, pp.2459-2468, PMLR, 10-15 July 2018."},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] Y. Luo, J. Zhu, M. Li, Y. Ren, and B. Zhang, \u201cSmooth neighbors on teacher graphs for semi-supervised learning,\u201d The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018. 10.1109\/cvpr.2018.00927","DOI":"10.1109\/CVPR.2018.00927"},{"key":"17","unstructured":"[17] J.T. Springenberg, \u201cUnsupervised and semi-supervised learning with categorical generative adversarial networks,\u201d International Conference on Learning Representations, 2016."},{"key":"18","unstructured":"[18] T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, \u201cImproved techniques for training gans,\u201d Advances in neural information processing systems, pp.2234-2242, 2016."},{"key":"19","unstructured":"[19] C. Li, T. Xu, J. Zhu, and B. Zhang, \u201cTriple generative adversarial nets,\u201d Advances in Neural Information Processing Systems 30, ed. I. Guyon, U.V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, pp.4088-4098, Curran Associates, Inc., 2017."},{"key":"20","unstructured":"[20] V. Dumoulin, I. Belghazi, B. Poole, O. Mastropietro, A. Lamb, M. Arjovsky, and A. Courville, \u201cAdversarially learned inference,\u201d International Conference on Learning Representations, 2017."},{"key":"21","unstructured":"[21] Z. Dai, Z. Yang, F. Yang, W.W. Cohen, and R.R. Salakhutdinov, \u201cGood semi-supervised learning that requires a bad gan,\u201d Advances in Neural Information Processing Systems 30, ed. I. Guyon, U.V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, pp.6510-6520, Curran Associates, Inc., 2017."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] X. Cao and N.Z. Gong, \u201cMitigating evasion attacks to deep neural networks via region-based classification,\u201d Proceedings of the 33rd Annual Computer Security Applications Conference, pp.278-287, ACM, 2017. 10.1145\/3134600.3134606","DOI":"10.1145\/3134600.3134606"},{"key":"23","unstructured":"[23] A. Fawzi, H. Fawzi, and O. Fawzi, \u201cAdversarial vulnerability for any classifier,\u201d Advances in Neural Information Processing Systems 31, ed. S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, pp.1178-1187, Curran Associates, Inc., 2018."},{"key":"24","unstructured":"[24] D. Rezende and S. Mohamed, \u201cVariational inference with normalizing flows,\u201d Proceedings of the 32nd International Conference on Machine Learning, ed. F. Bach and D. Blei, Proceedings of Machine Learning Research, vol.37, Lille, France, pp.1530-1538, PMLR, 07-09 July 2015."},{"key":"25","unstructured":"[25] D.P. Kingma, T. Salimans, R. Jozefowicz, X. Chen, I. Sutskever, and M. Welling, \u201cImproved variational inference with inverse autoregressive flow,\u201d Advances in Neural Information Processing Systems 29, ed. D.D. Lee, M. Sugiyama, U.V. Luxburg, I. Guyon, and R. Garnett, pp.4743-4751, Curran Associates, Inc., 2016."},{"key":"26","unstructured":"[26] G. Papamakarios, T. Pavlakou, and I. Murray, \u201cMasked autoregressive flow for density estimation,\u201d Advances in Neural Information Processing Systems 30, ed. I. Guyon, U.V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, pp.2338-2347, Curran Associates, Inc., 2017."},{"key":"27","unstructured":"[27] C.W. Huang, D. Krueger, A. Lacoste, and A. Courville, \u201cNeural autoregressive flows,\u201d Proceedings of the 35th International Conference on Machine Learning, ed. J. Dy and A. Krause, Proceedings of Machine Learning Research, vol.80, Stockholmsm\u00e4ssan, Stockholm Sweden, pp.2078-2087, PMLR, 10-15 July 2018."},{"key":"28","unstructured":"[28] L. Dinh, D. Krueger, and Y. Bengio, \u201cNice: Non-linear independent components estimation,\u201d International Conference on Learning Representations, 2015."},{"key":"29","unstructured":"[29] L. Dinh, J. Sohl-Dickstein, and S. Bengio, \u201cDensity estimation using real nvp,\u201d International Conference on Learning Representations, 2017."},{"key":"30","unstructured":"[30] P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P.A. Manzagol, \u201cStacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion,\u201d Journal of machine learning research, vol.11, no.Dec, pp.3371-3408, 2010."},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] Y. Li, S. Liu, J. Yang, and M.-H. Yang, \u201cGenerative face completion,\u201d The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017. 10.1109\/cvpr.2017.624","DOI":"10.1109\/CVPR.2017.624"},{"key":"32","unstructured":"[32] S. Ioffe and C. Szegedy, \u201cBatch normalization: Accelerating deep network training by reducing internal covariate shift,\u201d Proceedings of the 32nd International Conference on Machine Learning, ed. F. Bach and D. Blei, Proceedings of Machine Learning Research, vol.37, Lille, France, pp.448-456, PMLR, 07-09 July 2015."},{"key":"33","unstructured":"[33] A.L. Maas, A.Y. Hannun, and A.Y. Ng, \u201cRectifier nonlinearities improve neural network acoustic models,\u201d ICML Workshop on Deep Learning for Audio, Speech and Language Processing, 2013."},{"key":"34","unstructured":"[34] A. Radford, L. Metz, and S. Chintala, \u201cUnsupervised representation learning with deep convolutional generative adversarial networks,\u201d International Conference on Learning Representations, 2016."},{"key":"35","unstructured":"[35] K. Kolasinski, An implementation of the GLOW paper and simple normalizing flows lib, 2018."},{"key":"36","unstructured":"[36] J. Behrmann, P. Vicol, K.C. Wang, R. Grosse, and J.H. Jacobsen, \u201cUnderstanding and mitigating exploding inverses in invertible neural networks,\u201d Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, ed. A. Banerjee and K. Fukumizu, Proceedings of Machine Learning Research, vol.130, pp.1792-1800, PMLR, 13-15 April 2021."},{"key":"37","unstructured":"[37] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d International Conference on Learning Representations, 2015."},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] P. Haeusser, A. Mordvintsev, and D. Cremers, \u201cLearning by association-a versatile semi-supervised training method for neural networks,\u201d The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017. 10.1109\/cvpr.2017.74","DOI":"10.1109\/CVPR.2017.74"},{"key":"39","unstructured":"[39] J. Jackson and J. Schulman, \u201cSemi-supervised learning by label gradient alignment,\u201d arXiv preprint arXiv:1902.02336, 2019."},{"key":"40","unstructured":"[40] X. Chen, D.P. Kingma, T. Salimans, Y. Duan, P. Dhariwal, J. Schulman, I. Sutskever, and P. Abbeel, \u201cVariational lossy autoencoder,\u201d International Conference on Learning Representations, 2017."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/3\/E105.D_2021EDP7161\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T04:55:43Z","timestamp":1715230543000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/3\/E105.D_2021EDP7161\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,1]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2021edp7161","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,1]]},"article-number":"2021EDP7161"}}