{"type":"ScholarlyArticle","title":"Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels with Variational Auto-Encoder","authors":[{"name":"Weijia Zhang","slug":"weijia-zhang","given":"Weijia","family":"Zhang","affiliation":"School of Computer Science and Engineering , Southeast University , Nanjing 210096 , China"}],"abstract":"Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be identically and independently distributed, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Autoencoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.","doi":"10.24963/ijcai.2021/465","url":"https://ijcai.org/proceedings/2021/465","pdf":"https://ijcai.org/proceedings/2021/0465.pdf","markdown":"https://ijcai.org/proceedings/2021/465.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/465","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":465,"pages":{"first":3377,"last":3383},"keywords":["Machine Learning: Multi-instance; Multi-label; Multi-view learning","Machine Learning: Weakly Supervised Learning","Data Mining: Classification"],"videos":[],"references":[{"position":1,"raw":"[Amores, 2013] Jaume Amores. Multiple instance classifica- tion: Review, taxonomy and comparative study. Artificial Intelligence, 201:81-105, 2013.","title":"Jaume Amores. Multiple instance classification: Review, taxonomy and comparative study","authors":"Amores","year":"2013","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Andrews et al., 2002] Stuart Andrews, Ioannis Tsochan- taridis, and Thomas Hofmann. Support vector machines for multiple-instance learning. In Proceedings of the 15th International Conference on Neural Information Process- ing Systems (NeurIPS '02), pages 577-584, 2002.","title":"Support vector machines for multiple-instance learning","authors":"Stuart Andrews, Ioannis Tsochantaridis, Thomas Hofmann","year":"2002","venue":"Proceedings of the 15th International Conference on Neural Information Processing Systems (NeurIPS '02)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2006] Yixin Chen, Jinbo Bi, and J.Z. Wang. MILES: Multiple-instance learning via embedded instance selection. IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 28(12):1931-1947, 2006.","title":"MILES: Multiple-instance learning via embedded instance selection","authors":"Yixin Chen, Jinbo Bi, J Z Wang","year":"2006","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dietterich et al., 1997] Thomas G. Dietterich, Richard H. Lathrop, and Tomás Lozano-Pérez. Solving the multiple instance problem with axis-parallel rectangles. Artificial Intelligence, 89(1-2):31-71, 1997.","title":"Solving the multiple instance problem with axis-parallel rectangles","authors":"G Thomas, Richard H Dietterich, Tomás Lathrop, Lozano-Pérez","year":"1997","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Doran and Ray, 2016] Gary Doran and Soumya Ray. Multiple-instance learning from distributions. Journal of Machine Learning Research, 17(128):1-50, 2016.","title":"Multiple-instance learning from distributions","authors":"Ray ; Doran, Gary Doran, Soumya Ray","year":"2016","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Haussmann et al., 2017] Manuel Haussmann, Fred A. Hamprecht, and Melih Kandemir. Variational bayesian multiple instance learning with gaussian processes. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR '17). IEEE, 2017.","title":"Variational bayesian multiple instance learning with gaussian processes","authors":"Manuel Haussmann, Fred A Hamprecht, Melih Kandemir","year":"2017","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR '17)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ilse et al., 2018] Maximilian Ilse, Jakub Tomczak, and Max Welling. Attention-based deep multiple instance learning. In Proceedings of the 35th International Conference on Machine Learning (ICML '18), pages 2127-2136, 2018.","title":"Attention-based deep multiple instance learning","authors":"Maximilian Ilse, Jakub Tomczak, Max Welling","year":"2018","venue":"Proceedings of the 35th International Conference on Machine Learning (ICML '18)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ji et al., 2020] Yunjie Ji, Hao Liu, Bolei He, Xinyan Xiao, Hua Wu, and Yanhua Yu. Diversified multiple instance learning for document-level multi-aspect sentiment clas- sification. In Proceedings of the 2020 Conference on Em- pirical Methods in Natural Language Processing (EMNLP '20), pages 7012-7023, 2020.","title":"Diversified multiple instance learning for document-level multi-aspect sentiment classification","authors":"Yunjie Ji, Hao Liu, Bolei He, Xinyan Xiao, Hua Wu, Yanhua Yu","year":"2020","venue":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP '20)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kandemir and Hamprecht, 2014] Melih Kandemir and Fred A. Hamprecht. Instance label prediction by dirichlet process multiple instance learning. In Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence (UAI '14), 2014.","title":"Instance label prediction by dirichlet process multiple instance learning","authors":"Melih Kandemir, Fred A Hamprecht","year":"2014","venue":"Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence (UAI '14)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kim and la Torre, 2010] Minyoung Kim and Fernando De la Torre. Gaussian processes multiple instance learning minyoung. In Proceedings of the 27th International Con- ference on Machine Learning (ICML '10), 2010.","title":"Gaussian processes multiple instance learning minyoung","authors":"Minyoung Kim, Fernando De La, Torre","year":"2010","venue":"Proceedings of the 27th International Conference on Machine Learning (ICML '10)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma and Welling, 2014] Diederik P Kingma and Max Welling. Auto-encoding variational bayes. In Proceedings of the 2nd International Conference on Learning Repre- sentations (ICLR '14), 2014.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2014","venue":"Proceedings of the 2nd International Conference on Learning Representations (ICLR '14)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2009] Yu-Feng Li, James T.Kwok, Ivor W. Tsang, and Zhi-Hua Zhou. A convex method for locating regions of interest with multi-instance learning. In Proceedings of the European Conference on Machine Learning and Prin- ciples and Practice of Knowledge Discovery in Databases (ECML PKDD '09), 2009.","title":"A convex method for locating regions of interest with multi-instance learning","authors":"Yu-Feng Li, James T Kwok, Ivor W Tsang, Zhi-Hua Zhou","year":"2009","venue":"Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD '09)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Shi et al., 2020] Xiaoshuang Shi, Fuyong Xing, Yuanpu Xie, Zizhao Zhang, Lei Cui, and Lin Yang. Loss-based at- tention for deep multiple instance learning. Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI '20), pages 5742-5749, 2020.","title":"Loss-based attention for deep multiple instance learning","authors":"Shi","year":"2020","venue":"Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI '20)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Sirinukunwattana et al., 2016] Korsuk Sirinukunwattana, Shan E Ahmed Raza, Yee-Wah Tsang, David R. J. Snead, Ian A. Cree, and Nasir M. Rajpoot. Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. IEEE Transactions on Medical Imaging, 35(5):1196-1206, 2016.","title":"Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images","authors":"Sirinukunwattana","year":"2016","venue":"IEEE Transactions on Medical Imaging","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Skrede et al., 2020] Ole-Johan Skrede, Sepp De Raedt, An- dreas Kleppe andTarjei S Hveem, Knut Liestøl, John Mad- dison, Hanne A Askautrud, Manohar Pradhan, John Arne Nesheim, Fritz Albregtsen, Inger Nina Farstad, Enric Domingo, David N Church, Arild Nesbakken, Neil A Shepherd, Ian Tomlinson, Rachel Kerr, Marco Novelli, David J Kerr, and Håvard E Danielsen. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. The Lancet, 35(10221):350-360, 2020.","title":"Deep learning for prediction of colorectal cancer outcome: a discovery and validation study","authors":"Skrede","year":"2020","venue":"The Lancet","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wang et al., 2018] Xinggang Wang, Yongluan Yan, Peng Tang, Xiang Bai, and Wenyu Liu. Revisiting multiple in- stance neural networks. Pattern Recognition, 74:15-24, 2018.","title":"Revisiting multiple instance neural networks","authors":"Wang","year":"2018","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Wei et al., 2017] Xiu-Shen Wei, Jianxin Wu, and Zhi-Hua Zhou. Scalable algorithms for multi-instance learning. IEEE Transactions on Neural Networks and Learning Sys- tems, 28(4):975-987, 2017.","title":"Scalable algorithms for multi-instance learning","authors":"Xiu-Shen Wei, Jianxin Wu, Zhi-Hua Zhou","year":"2017","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Xu et al., 2019] Bi-Cun Xu, Kai Ming Ting, and Zhi-Hua Zhou. Isolation set-kernel and its application to multi- instance learning. In Proceedings of The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '19), pages 941-949, 2019.","title":"Isolation set-kernel and its application to multiinstance learning","authors":"Bi-Cun, Kai Xu, Ming Ting, Zhi-Hua Zhou","year":"2019","venue":"Proceedings of The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '19)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yao et al., 2020] Jiawen Yao, Xinliang Zhu, Jitendra Jonna- gaddala, Nicholas Hawkins, and Junzhou Huang. Whole slide images based cancer survival prediction using at- tention guided deep multiple instance learning networks. Medical Image Analysis, 65:101789, 2020.","title":"Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks","authors":"Jiawen Yao, Xinliang Zhu, Jitendra Jonnagaddala, Nicholas Hawkins, Junzhou Huang","year":"2020","venue":"Medical Image Analysis","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhang and Zhou, 2014] Weijia Zhang and Zhi-Hua Zhou. Multi-instance learning with distribution change. In Pro- ceedings of the 28th AAAI Conference on Artificial Intelli- gence (AAAI '14), pages 2184-2190, 2014.","title":"Multi-instance learning with distribution change","authors":"Weijia Zhang, Zhi-Hua Zhou","year":"2014","venue":"Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI '14)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhou et al., 2009] Zhi-Hua Zhou, Yu-Yin Sun, and Yu- Feng Li. Multi-instance learning by treating instances as non-i.i.d. samples. In Proceedings of the 26th Inter- national Conference on Machine Learning (ICML '09), pages 1249-1256, 2009.","title":"Multi-instance learning by treating instances as non-i.i.d. samples","authors":"Zhi-Hua Zhou, Yu-Yin Sun, Yu-Feng Li","year":"2009","venue":"Proceedings of the 26th International Conference on Machine Learning (ICML '09)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}