Optimization of interaction losses for ranking and self-supervised learning - Internship - Naver Labs Europe
23 October 2020
Meylan, Grenoble, France, France
Start date
6 months


Interaction losses [1] are defined between data examples rather than on one example as in classification or regression. They are becoming ubiquitous in machine learning, especially in text and image retrieval [2, 3], self-supervised pre-training [4], and start being considered in the context of unsupervised learning. Unfortunately, such losses are known to be difficult to optimize [5] because the joint optimal setting of the different variables that control training (batch size, learning rate, class-balanced sampling, choice of using part vs all interactions) does usually not scale in the same way as it does for single-example losses. Various strategies already exist to deal with this challenge [6, 7, 8]. The 6-month internship will be organized in two main parts. First, we will extend our existing benchmark of these approaches. In a second part, we will develop and evaluate extensions of them.

Required skills

* PhD level, or research-oriented master level.

* Good background in machine learning, mathematics and statistics

* Good coding skills in Python and Pytorch or another framework


[1] Hadsell, R., Chopra, S., & LeCun, Y. (2006, June). Dimensionality reduction by learning an invariant mapping. In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) (Vol. 2, pp. 1735-1742). IEEE.

[2] Liu, T. Y. (2011). Learning to rank for information retrieval. Springer Science & Business Media.

[3] Gordo, A., Almazán, J., Revaud, J., & Larlus, D. (2016, October). Deep image retrieval: Learning global representations for image search. In European conference on computer vision (pp. 241-257). Springer, Cham.

[4] Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709.

[5] Wu, C. Y., Manmatha, R., Smola, A. J., & Krahenbuhl, P. (2017). Sampling matters in deep embedding learning. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2840-2848).

[6] Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 815-823).

[7] He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9729-9738).

[8] Wang, X., Zhang, H., Huang, W., & Scott, M. R. (2020). Cross-Batch Memory for Embedding Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 6388-6397).

Application instructions

You can apply for this position online. Don't forget to upload your CV and cover letter before you submit. Incomplete applications will not be accepted.
Due to the changing travel restrictions related to COVID-19, it may not be possible to host candidates from certain regions. This will depend on the conditions at the specific starting date of the internship.


NAVER LABS Europe has full-time positions, PhD and PostDoc opportunities throughout the year which are advertised here and on international conference sites that we sponsor such as CVPR, ICCV, ICML, NeurIPS, EMNLP etc.

NAVER LABS Europe is an equal opportunity employer.

NAVER LABS are in Grenoble in the French Alps. We have a multi and interdisciplinary approach to research with scientists in machine learning, computer vision, artificial intelligence, natural language processing, ethnography and UX working together to create next generation ambient intelligence technology and services that deeply understand users and their contexts.

Apply to this internship
Drop files here browse files ...
Drop files here browse files ...
Drop files here browse files ...

Related Jobs

25 November 2020
Full Body 3D Human Pose in the Wild - Internship   Meylan, Grenoble, France, France
19 November 2020
16 November 2020
Learning to grasp as a human demonstration - Internship   Meylan, Grenoble, France, France
16 November 2020
9 November 2020
Are you sure you want to delete this file?