Lifelong Representation Learning- MIAI - NAVER LABS Europe

Lifelong Representation Learning

Naver Labs Europe is leading a chair on Lifelong Representation Learning as part of  the MIAI institute.

MIAI Grenoble Alpes (Multidisciplinary Institute in Artificial Intelligence) aims to conduct research in artificial intelligence at the highest level, to offer attractive courses for students and professionals of all levels, to support innovation in large companies, SMEs and startups and to inform and interact with citizens on all aspects of AI.


Naver Labs Europe is leading a chair on Lifelong Representation Learning which is one of the three chairs of the machine learning and reasoning line of research of the MIAI institute:

  • Towards Robust and Understandable Neuromorphic Systems – Sophie Achard & Martial Mermillod
  • Lifelong Representation Learning – Diane Larlus & Florent Perronnin
  • Towards More Data Efficiency in Machine Learning – Julien Mairal

All together, these three chairs are tackling the following problem:
Despite their success, huge-dimensional machine learning models such as multilayer neural networks are lacking crucial stability properties, making them dependent on huge sets of annotated data. We are planning to tackle this problem through multiple complementary angles. We will develop theoretically-grounded regularisation principles for high-dimensional models to make them more data-efficient, introduce new learning paradigms that will allow us to leverage multiple learning tasks sequentially, propose new transfer learning approaches, and explore other paradigms inspired by cognitive sciences.” (More info on the MIAI website)

Lifelong Representation Learning

Given a set of problems to solve, the dominant paradigm in the AI community has been to solve each problem or task independently. This is in sharp contrast with the human capability to build from past experience and transfer knowledge to speed-up the learning process for a new task. To mimic such a capability, the machine learning community has introduced the concept of continual learning or lifelong learning. The main advantage of this paradigm is that it enables learning with less data, it often allows to learn faster and to generalize better. From an industrial standpoint, the potential of lifelong learning is tremendous as this would mean deploying machine learning models faster by bypassing the need to collect and label.


Blog post