May, Tuesday 31st

14:30 (Shannon amphitheatre, 'Digiteo Shannon' 660 building) (see location)

François Gonard

(TAU team)

PhD defense: Cold-start recommendation: from algorithm portfolios to job applicant matching


Abstract

The need for personalized recommendations is motivated by the overabundance of online information, products, social connections. This typically tackled by recommender systems (RS) that learn users interests from past recorded activities. Another context where recommendation is desirable is when estimating the relevance of an item requires complex reasoning based on experience. Machine learning techniques are good candidates to simulate experience with large amounts of data.
The present thesis focuses on the cold-start context in recommendation, i.e. the situation where either a new user desires recommendations or a brand-new item is to be recommended. Since no past interaction is available, RSs have to base their reasoning on side descriptions to form recommendations. Two of such recommendation problems are investigated in this work. Recommender systems designed for the cold-start context are designed.
The problem of choosing an optimization algorithm in a portfolio can be cast as a recommendation problem. We propose a two components system combining a per-instance algorithm selector and a sequential scheduler to reduce the optimization cost of a brand-new problem instance and mitigate the risk of optimization failure. Both components are trained with past data to simulate experience, and alternatively optimized to enforce their cooperation. The final system won the Open Algorithm Challenge 2017.
Automatic job-applicant matching (JAM) has recently received considerable attention in the recommendation community for applications in online recruitment platforms. We develop specific natural language (NL) modeling techniques and combine them with standard recommendation procedures to leverage past user interactions and the textual descriptions of job positions. The NL and recommendation aspects of the JAM problem are studied on two real-world datasets. The appropriateness of various RSs on applications similar to the JAM problem are discussed.


Supervision:

Marc Schoenauer, Michèle Sebag

Jury:

M. Patrick GALLINARI - Université Pierre et Marie Curie - Reviewer
M. Holger HOOS - Universiteit Leiden - Reviewer
Mme Anne VILNAT - Université Paris-Sud - Examiner
M. Amaury HABRARD - Université Jean Monnet Saint-Etienne - Examiner
M. Jin-Kao HAO - Université d'Angers - Examiner
M. Yves TOURBIER - Renault SAS - Invited