Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning

Résumé

We use the maximum a posteriori estimation principle for learning representations distributed on the unit sphere. We propose to use the angular Gaussian distribution, which corresponds to a Gaussian projected on the unit-sphere and derive the associated loss function. We also consider the von Mises-Fisher distribution, which is the conditional of a Gaussian in the unit-sphere. The learned representations are pushed toward fixed directions, which are the prior means of the Gaussians; allowing for a learning strategy that is resilient to data drift. This makes it suitable for online continual learning, which is the problem of training neural networks on a continuous data stream, where multiple classification tasks are presented sequentially so that data from past tasks are no longer accessible, and data from the current task can be seen only once. To address this challenging scenario, we propose a memory-based representation learning technique equipped with our new loss functions. Our approach does not require negative data or knowledge of task boundaries and performs well with smaller batch sizes while being computationally efficient. We demonstrate with extensive experiments that the proposed method outperforms the current state-of-the-art methods on both standard evaluation scenarios and realistic scenarios with blurry task boundaries. For reproducibility, we use the same training pipeline for every compared method and share the code at https://t.ly/SQTj.
Fichier principal
Vignette du fichier
2306.03364.pdf (715.95 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04425481 , version 1 (30-01-2024)

Identifiants

Citer

Nicolas Michel, Giovanni Chierchia, Romain Negrel, Jean-François Bercher. Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning. The 38th Annual AAAI Conference on Artificial Intelligence, Feb 2024, Vancouver, Canada. ⟨10.48550/arXiv.2306.03364⟩. ⟨hal-04425481⟩
35 Consultations
60 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More