Portrait de Abdel Mfougouon Njupoun

Abdel Mfougouon Njupoun

abdelnjupoun@gmail.com
Doctorat - UdeM
Superviseur⋅e principal⋅e
Guillaume Lajoie
Co-supervisor
Blake Richards
Sujets de recherche
Apprentissage par renforcement
Neurosciences computationnelles
Systèmes dynamiques
Théorie de l'apprentissage automatique
Site web
Google Scholar
GitHub

Publications

Gated Target Propagation for Compositional Generalization in Continual Learning
Abdel Mfougouon Njupoun
Colin Bredenberg
Blake Aaron Richards
Guillaume Lajoie
Continual learning is typically framed as acquiring new knowledge without catastrophically forgetting previous tasks. However, a flexible co… (voir plus)ntinual learner should also be able to reuse and recombine previously acquired knowledge to rapidly solve novel task compositions. We introduce Gated Target Propagation (GaTaP), a continual learning algorithm in which task-specific gating variables---learned through a closed-form inner loop update---selectively suppress or enhance network modules. Network parameters are learned in a slower timescale outer loop, using the same local difference target propagation error signal as is used for adapting gating variables. We provide tractable experiments on class-incremental learning scenarios for both multilayer perceptron and convolutional network architectures. We show strong performance retention on previously learned tasks, as well as compositional generalization to unseen tasks, achieved through few-shot gain adaptation at inference. We analyze learned gating patterns and find that related tasks exhibit similar gating patterns, suggesting that inferred gates capture meaningful, reusable task structure. Overall, GaTaP provides a powerful framework for jointly ameliorating catastrophic forgetting and enabling few-shot compositional generalization in neural network models.
2026-10-02
arXiv (prépublication)
doi.org
arxiv.org