MALT is a joint project-team between Inria (Centre Inria de l’Université de Rennes), Université de Rennes, and Université Rennes 2 hosted at IRISA (Institut de Recherche en Informatique et Systèmes Aléatoires).  Our work spans three key areas:

 

• Machine learning models on temporal data (sequences and time series) with questions around embeddings, generation of such data, and early predictions.
• Adapting machine learning models to evolving data and class distributions over time, with questions around domain adaptation, continual learning, and sequential learning.
• Trustworthiness of temporal models with questions around explanations, privacy, fairness, robustness, efficiency, and generalization of such models.