Jill-Jênn Vie

Research Scientist at Inria

We are hiring engineers to work on Covid-19 data. Please get in touch if interested.
Recording from our Optimizing Human Learning workshop (WASL 2020 @ AIED) is available.

I am a permanent research scientist at Inria in the Scool team, interested in online factorization, deep generative models and educational applications of machine learning. I am now a board member of the French Computer Science Society (SIF).

Feel free to contact: vie@jill-jenn.net or Twitter.

Research Interests

Deep generative models of human learning: If we can generate log data from educational platforms (e.g. MOOCs), we can predict, explain and optimize student performance.
See our tutorial about knowledge tracing and the slides of our presentation in IIT Hyderabad.
Recommender systems with side information: How to model uncertainty and side information in preference elicitation? See our demo Mangaki in 5 languages and keynote.
Using 330k ratings from Mangaki data, we organized a data challenge with Kyoto University [problem] [solutions].
Adaptive testing for optimizing human learning: How to optimize human learning by selecting the next item to ask? See our workshop.
Multidimensional item response theory, cognitive diagnosis [slides], multistage testing, determinantal point processes [slides] [code].

Our article **Knowledge Tracing Machines** has been presented at **AAAI 2019**. See also our code & tutorial (Vie and Kashima 2019).

Our paper **Using Posters to Recommend Anime and Mangas in a Cold-Start Scenario** [arXiv] [slides] has been accepted to **MANPU 2017**.

We received the **Best Paper Award** at **EDM 2019** for our learning/forgetting student model **DAS3H** (Choffin et al. 2019).

Other Achievements

✅ I designed and implemented free software that is used to certify the digital skills of every French citizen
✅ Organizing chair of PyParis 2017–2018, Educational Data Mining 2019, Optimizing Human Learning 2018–2020.
✅ Reviewer for IEEE-Transactions on Learning Technologies (IEEE-TLT), Journal of Educational Data Mining (JEDM)
✅ We organized a programming summer school for K-12 girls → Girls Can Code! running since 2014
✅ We wrote & directed a TV show about algorithms that take control of our lives → La Faute à l’algo (Blame the Algorithm). Fun fact, our TV show was mentioned by the French Senate as an interesting example of popularization of AI

Selected Publications

See all publications / My Scholar page

Choffin, Benoı̂t, Fabrice Popineau, Yolaine Bourda, and Jill-Jênn Vie. 2019. “DAS3H: Modeling Student Learning and Forgetting for Optimally Scheduling Distributed Practice of Skills.” In Proceedings of the Twelfth International Conference on Educational Data Mining (EDM 2019), 29–38. https://arxiv.org/abs/1905.06873.

Vie, Jill-Jênn, and Hisashi Kashima. 2019. “Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing.” In Proceedings of the 33th AAAI Conference on Artificial Intelligence, 750–57. https://arxiv.org/abs/1811.03388.