{"type":"ScholarlyArticle","title":"Learning Realistic Patterns from Visually Unrealistic Stimuli: Generalization and Data Anonymization (Extended Abstract)","authors":[{"name":"Konstantinos Nikolaidis","slug":"konstantinos-nikolaidis","given":"Konstantinos","family":"Nikolaidis","affiliation":"Department of Informatics , University of Oslo , Norway"},{"name":"Stein Kristiansen","slug":"stein-kristiansen","given":"Stein","family":"Kristiansen","affiliation":"Department of Informatics , University of Oslo , Norway"},{"name":"Thomas Plagemann","slug":"thomas-plagemann","given":"Thomas","family":"Plagemann","affiliation":"Department of Informatics , University of Oslo , Norway"},{"name":"Vera Goebel","slug":"vera-goebel","given":"Vera","family":"Goebel","affiliation":"Department of Informatics , University of Oslo , Norway"},{"name":"Knut Liestøl","slug":"knut-liest-l","given":"Knut","family":"Liestøl","affiliation":"Department of Informatics , University of Oslo , Norway"},{"name":"Mohan Kankanhalli","slug":"mohan-kankanhalli","given":"Mohan","family":"Kankanhalli","affiliation":"Department of Computer Science , National University of Singapore , Singapore"},{"name":"Gunn-Marit Traaen","slug":"gunn-marit-traaen","given":"Gunn-Marit","family":"Traaen","affiliation":"Department of Cardiology , Oslo University Hospital Rikshospitalet , Oslo , Norway"},{"name":"Britt Øverland","slug":"britt-verland","given":"Britt","family":"Øverland","affiliation":"Department of Otorhinolaryngology , Sleep Unit Lovisenberg Diakonale Hospital , Oslo , Norway"},{"name":"Harriet Akre","slug":"harriet-akre","given":"Harriet","family":"Akre","affiliation":"Institute of Clinical Medicine , Faculty of Medicine , University of Oslo , Oslo , Norway"},{"name":"Lars Aakeroy","slug":"lars-aakeroy","given":"Lars","family":"Aakeroy","affiliation":"Department of Circulation and Medical Imaging , Norwegian University of Science and Technology , Trondheim , Norway"},{"name":"Sigurd Steinshamn","slug":"sigurd-steinshamn","given":"Sigurd","family":"Steinshamn","affiliation":"Department of Circulation and Medical Imaging , Norwegian University of Science and Technology , Trondheim , Norway"}],"abstract":"Good training data is a prerequisite to develop useful Machine Learning applications. However, in many domains existing data sets  cannot be shared due to privacy regulations (e.g., from medical studies). This work investigates a simple yet unconventional approach for anonymized data synthesis to enable third parties to benefit from such anonymized data. We explore the feasibility of learning implicitly from visually unrealistic, task-relevant stimuli, which are synthesized by exciting the neurons of a  trained  deep neural network. As such, neuronal excitation can be used to generate synthetic stimuli.  The stimuli data is used to train new classification models. Furthermore, we extend this framework to inhibit representations that are associated with specific individuals. Extensive comparative empirical investigation  shows that different algorithms trained on the stimuli are able to generalize successfully on  the same task as the original model.","doi":"10.24963/ijcai.2022/806","url":"https://ijcai.org/proceedings/2022/806","pdf":"https://ijcai.org/proceedings/2022/0806.pdf","markdown":"https://ijcai.org/proceedings/2022/806.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/806","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Journal Track","track":"Journal Track","number":806,"pages":{"first":5762,"last":5766},"keywords":["Natural Language Processing: Knowledge Extraction","Computer Vision: Neural generative models, auto encoders, GANs","Computer Vision: Representation Learning","Knowledge Representation and Reasoning: General"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987238","length_sec":83,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985381","length_sec":586,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Arjovsky et al., 2017] Martin Arjovsky, Soumith Chintala, and Léon Bottou. Wasserstein generative adversarial net- works. In Doina Precup and Yee Whye Teh, editors, Pro- ceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 214-223, International Convention Cen- tre, Sydney, Australia, 06-11 Aug 2017. PMLR.","title":"Wasserstein generative adversarial networks","authors":"Arjovsky","year":"2017","venue":"Proceedings of the 34th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baluja and Fischer, 2017] Shumeet Baluja and Ian Fis- cher. Adversarial transformation networks: Learn- ing to generate adversarial examples. arXiv preprint, arXiv:1703.09387, 2017.","title":"Adversarial transformation networks: Learning to generate adversarial examples","authors":"Fischer Baluja","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Erhan et al., 2009] Dumitru Erhan, Yoshua Bengio, Aaron Courville, and Pascal Vincent. Visualizing higher-layer features of a deep network. University of Montreal, 1341(3):1, 2009.","title":"Visualizing higher-layer features of a deep network","authors":"Yoshua Dumitru Erhan, Aaron Bengio, Pascal Courville, Vincent","year":"2009","venue":"University of Montreal","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Feutry et al., 2018] Clément Feutry, Pablo Piantanida, Yoshua Bengio, and Pierre Duhamel. Learning anonymized representations with adversarial neural networks. arXiv preprint, arXiv:1802.09386, 2018.","title":"Learning anonymized representations with adversarial neural networks","authors":"Clément Feutry, Pablo Piantanida, Yoshua Bengio, Pierre Duhamel","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Kairouz et al., 2019] Peter Kairouz, Jiachun Liao, Chong Huang, and Lalitha Sankar. Censored and fair universal representations using generative adversarial models. arXiv preprint, arXiv:1910.00411, 2019.","title":"Censored and fair universal representations using generative adversarial models","authors":"Peter Kairouz, Jiachun Liao, Chong Huang, Lalitha Sankar","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kingma and Welling, 2013] Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint, arXiv:1312.6114, 2013.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kristiansen et al., 2021] Stein Kristiansen, Konstantinos Nikolaidis, Thomas Plagemann, Vera Goebel, Gunn Marit Traaen, Britt Øverland, Lars Aakerøy, Tove-Elizabeth Hunt, Jan Pål Loennechen, Sigurd Loe Steinshamn, et al. A clinical evaluation of a low-cost strain gauge respiration belt and machine learning to detect sleep apnea. arXiv preprint, arXiv:2101.02595, 2021.","title":"A clinical evaluation of a low-cost strain gauge respiration belt and machine learning to detect sleep apnea","authors":"Konstantinos Stein Kristiansen, Thomas Nikolaidis, Vera Plagemann, Gunn Goebel, Britt Marit Traaen, Lars Øverland, Tove-Elizabeth Aakerøy, Jan Hunt, Sigurd Pål Loennechen, Loe Steinshamn","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Nguyen et al., 2015] Anh Nguyen, Jason Yosinski, and Jeff Clune. Deep neural networks are easily fooled: High con- fidence predictions for unrecognizable images. In The IEEE Conference on Computer Vision and Pattern Recog- nition (CVPR), June 2015.","title":"Deep neural networks are easily fooled: High confidence predictions for unrecognizable images","authors":"Anh Nguyen, Jason Yosinski, Jeff Clune","year":"2015","venue":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Nguyen et al., 2016] Anh Nguyen, Alexey Dosovitskiy, Ja- son Yosinski, Thomas Brox, and Jeff Clune. Synthesiz- ing the preferred inputs for neurons in neural networks via deep generator networks. In Advances in Neural Informa- tion Processing Systems, pages 3387-3395, 2016.","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","authors":"Anh Nguyen, Alexey Dosovitskiy, Jason Yosinski, Thomas Brox, Jeff Clune","year":"2016","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Nikolaidis et al., 2021] Konstantinos Nikolaidis, Stein Kristiansen, Thomas Plagemann, Vera Goebel, Knut Liestøl, Mohan Kankanhalli, Gunn Marit Traaen, Britt Overland, Harriet Akre, Lars Aakerøy, et al. Learning realistic patterns from visually unrealistic stimuli: Gen- eralization and data anonymization. Journal of Artificial Intelligence Research, 72:1163-1214, 2021.","title":"Learning realistic patterns from visually unrealistic stimuli: Generalization and data anonymization","authors":"Konstantinos Nikolaidis, Thomas Stein Kristiansen, Vera Plagemann, Knut Goebel, Mohan Liestøl, Gunn Kankanhalli, Britt Marit Traaen, Harriet Overland, Lars Akre, Aakerøy","year":"2021","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Ponce et al., 2019] Carlos R Ponce, Will Xiao, Peter F Schade, Till S Hartmann, Gabriel Kreiman, and Mar- garet S Livingstone. Evolving images for visual neurons using a deep generative network reveals coding principles and neuronal preferences. Cell, 177(4):999-1009, 2019.","title":"Evolving images for visual neurons using a deep generative network reveals coding principles and neuronal preferences","authors":"Will Carlos R Ponce, Xiao, Peter F Schade, S Till, Gabriel Hartmann, Margaret S Kreiman, Livingstone","year":"2019","venue":"Cell","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Reber, 1989] Arthur S Reber. Implicit learning and tacit knowledge. Journal of experimental psychology: General, 118(3):219, 1989.","title":"Implicit learning and tacit knowledge","authors":"Arthur S Reber","year":"1989","venue":"Journal of experimental psychology: General","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}