Learning Realistic Patterns from Visually Unrealistic Stimuli: Generalization and Data Anonymization (Extended Abstract)

Konstantinos Nikolaidis, Stein Kristiansen, Thomas Plagemann, Vera Goebel, Knut Liestøl, Mohan S. Kankanhalli, Gunn Marit Traaen, Britt Øverland, Harriet Akre, Lars Aakerøy, Sigurd Steinshamn

IJCAI 2022 pp. 5762-5766

doi:10.24963/IJCAI.2022/806 /ijcai/2022/nikolaidis2022ijcai-learning/

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.

PDF IJCAI Semantic Scholar

Cite

Text

Nikolaidis et al. "Learning Realistic Patterns from Visually Unrealistic Stimuli: Generalization and Data Anonymization (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/806

Markdown

[Nikolaidis et al. "Learning Realistic Patterns from Visually Unrealistic Stimuli: Generalization and Data Anonymization (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/nikolaidis2022ijcai-learning/) doi:10.24963/IJCAI.2022/806

BibTeX

@inproceedings{nikolaidis2022ijcai-learning,
  title     = {{Learning Realistic Patterns from Visually Unrealistic Stimuli: Generalization and Data Anonymization (Extended Abstract)}},
  author    = {Nikolaidis, Konstantinos and Kristiansen, Stein and Plagemann, Thomas and Goebel, Vera and Liestøl, Knut and Kankanhalli, Mohan S. and Traaen, Gunn Marit and Øverland, Britt and Akre, Harriet and Aakerøy, Lars and Steinshamn, Sigurd},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {5762-5766},
  doi       = {10.24963/IJCAI.2022/806},
  url       = {https://mlanthology.org/ijcai/2022/nikolaidis2022ijcai-learning/}
}