Design of an Explainable Machine Learning Challenge for Video Interviews - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

Design of an Explainable Machine Learning Challenge for Video Interviews

Abstract

This paper reviews and discusses research advances on “explainable machine learning” in computer vision. We focus on a particular area of the “Looking at People” (LAP) thematic domain: first impressions and personality analysis. Our aim is to make the computational intelligence and computer vision communities aware of the importance of developing explanatory mechanisms for computer-assisted decision making applications, such as automating recruitment. Judgments based on personality traits are being made routinely by human resource departments to evaluate the candidates' capacity of social insertion and their potential of career growth. However, inferring personality traits and, in general, the process by which we humans form a first impression of people, is highly subjective and may be biased. Previous studies have demonstrated that learning machines can learn to mimic human decisions. In this paper, we go one step further and formulate the problem of explaining the decisions of the models as a means of identifying what visual aspects are important, understanding how they relate to decisions suggested, and possibly gaining insight into undesirable negative biases. We design a new challenge on explainability of learning machines for first impressions analysis. We describe the setting, scenario, evaluation metrics and preliminary outcomes of the competition. To the best of our knowledge this is the first effort in terms of challenges for explainability in computer vision. In addition our challenge design comprises several other quantitative and qualitative elements of novelty, including a “coopetition” setting, which combines competition and collaboration.
Fichier principal
Vignette du fichier
design-explainable-machine.pdf (1.27 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01668386 , version 1 (05-01-2018)

Identifiers

Cite

Hugo Jair Escalante, Isabelle Guyon, Sergio Escalera, Julio Jacques, Meysam Madadi, et al.. Design of an Explainable Machine Learning Challenge for Video Interviews. IJCNN 2017 - 30th International Joint Conference on Neural Networks, May 2017, Anchorage, AK, United States. pp.1-8, ⟨10.1109/IJCNN.2017.7966320⟩. ⟨hal-01668386⟩
1515 View
1954 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More