Presentation
Machine learning can be used to analyze and extract value from the massive amounts of data produced by people and organizations. As the predictive performance increases with the size of the training dataset, it is desirable to train machine learning algorithms on data shared across multiple parties rather than on individual, smaller datasets. For instance, a single hospital holds data about only a few patients for a given disease, companies in different sectors may want to collaborate to cluster their common clients into groups, and personalized services such as content recommendation greatly improve when leveraging data collected from a large number of users. Unfortunately, sharing data across multiple parties may be impossible due to legislation or IP restrictions, and can pose important risks regarding the privacy of individuals. An important challenge is therefore to develop privacy-preserving algorithms to learn from datasets distributed across multiple data owners who do not want to share their data.
This workshop serves as kick-off to PAD-ML (Privacy-Aware Distributed Machine Learning), an Inria North-European Associate Team between the Magnet project-team (Inria) and the Privacy-preserving data analysis group (Alan Turing Institute) which officially started in September 2018. Researchers from both groups will present recent/ongoing work and discuss some open challenges.
Location & Dates
The workshop will take place on October 25, 2018 at Inria Lille (France). Lille is the capital of the north of France, a metropolis with 1 million inhabitants, with excellent train connection to Brussels (34 min), Paris (60 min) and London (80 min). See how to get there.
Registration
Registration is free but mandatory. Click here to register.
Confirmed speakers
- Aurélien Bellet (Inria)
- Daphne Ezer (Alan Turing Institute & Warwick)
- Adrià Gascón (Alan Turing Institute & Warwick)
- Matt Kusner (Alan Turing Institute)
- Jan Ramon (Inria)
Schedule
All events are located in the Amphitheater (Building B).
Thursday, October 25th, 2018
2:00pm – 2:05pm | Workshop presentation |
2:05pm – 3:05pm | Adrià Gascón/Matt Kusner: Secure Computation & Machine Learning: recent developments and next steps [abstract] |
3:05pm – 4:05pm | Jan Ramon: Privacy preserving learning in the curious and not so honest setting [abstract] |
4:05pm – 4:30pm | Coffee break |
4:30pm – 5:30pm | Daphne Ezer: Open challenges in privacy-preserving genomics research [abstract] |
5:30pm – 6:30pm | Aurélien Bellet: The natural privacy of gossip protocols: first results and open questions [abstract] |
Organizers
- Aurélien Bellet (Inria)
- Adrià Gascón (Alan Turing Institute & Warwick)
Financial support
The workshop is organized in the context of PAD-ML (Privacy-Aware Distributed Machine Learning), an Inria North-European Associate Team between the Magnet project-team (Inria) and the Privacy-preserving data analysis group (Alan Turing Institute). We are grateful to our sponsors, listed below.