AFCHAR Darius

PhD student
Team : MLIA
Arrival date : 12/01/2020
    Sorbonne Université - LIP6
    Boîte courrier 169
    Couloir 26-00, Étage 5, Bureau 534
    4 place Jussieu
    75252 PARIS CEDEX 05
    FRANCE

Tel: +33 1 44 27 39 44, Darius.Afchar (at) nulllip6.fr
https://lip6.fr/Darius.Afchar

Supervision : Patrick GALLINARI

Co-supervision : GUIGUE Vincent (LIP6)

Interpretable Machine Learning for Music Recommendation

Interpretability (or explainable Artificial Intelligence (AI)) is a crucial topic in machine learning. More and more modern fields use machine learning techniques, especially deep neural networks, to predict, classify, recommend and generate content. But the growing number of their computations units and millions of parameters is often considered detrimental to the ability to explain how they operate (black-box models) compared to more traditional methods such as decision trees or linear regressions for which the computation is simple enough to be fully rationalised (white-box models). Yet, interpretability is absolutely needed in many cases, as in the medical field, and generally with any task that involves sensitive data or requires to check the fairness of the decision process [1]. Beyond them, interpretability is a currently trending subject in many more fields because of its highly informative value. For users of a recommender system, for instance, it is a way to prevent the usual misunderstanding of why an item was recommended to them (imagine generating a nameless music playlist versus a one that is "based on" their favourite artists, a mood, a dynamic interaction) and for engineers and researchers, it is all about the how, it is a way to identify bias, flaws or redundancies in their models, choose its best configuration and create more efficient ones. The goal of this PhD is to overthrow the preconceived idea that deep learning models are necessarily black-box, and to build deep complex models that are also explainable for music