Semantic Anchors Facilitate Task Encoding in Continual Learning

Bibliographic Data

ID22157692
AuthorsMina Habibi (0000-0003-4287-3574, Ghent University), Pieter Verbeke (0000-0003-2919-1528, University College West Flanders), Mehdi Senoussi (0000-0001-9896-4235, Centre National de la Recherche Scientifique), Senne Braem (0000-0002-2619-8225, Ghent University)
Year2025
Volume9
Pages1467-1505
Publication date2025-09-26
Open AccessYes
TypeARTICLE
VenueOpen MIND (JOURNAL)
Journal identifiersISSN: 2470-2986 • E-ISSN: 2470-2986
PublisherMIT Press (PUBLISHER • US)
DOI10.1162/opmi.a.28
PMID41036497
OpenAlexW4414780477
LanguageEN
References cited104

Humans are remarkably efficient at learning new tasks, in large part by relying on the integration of previously learned knowledge. However, research on task learning typically focuses on the learning of abstract task rules on minimalist stimuli, to study behavior independent of the learning history that humans come equipped with (i.e., semantic knowledge). In contrast, several theories suggest that the use of semantic knowledge and labels may help the learning of new task information. Here, we tested whether providing existing, semantically rich task embeddings and response labels allowed for more robust task rule encoding and less (catastrophic) forgetting and interference. Our results show that providing semantically rich task settings and response labels resulted in less task forgetting (Experiment 1), both when using pictorial symbols or words as labels (Experiment 2), or when contrasted with visually matched shape labels without inherent meaning (Experiment 4). Using a subsequent value-based decision-making task and reinforcement learning modeling (Experiment 3), we demonstrate how the learned embedding of novel stimuli in semantically rich, representations, further allowed for a more efficient, feature-specific processing when learning new task information. Finally, using artificial recurrent neural networks fitted to our participants’ task performance, we found that task separation during learning was more predictive of learning and task performance in the semantically rich conditions. Together, our findings show the benefit of using semantically rich task rules and response labels during novel task learning, thereby offering important insights into why humans excel in continual learning and are less susceptible to catastrophic forgetting compared to most artificial agents

Forgetting · Multi-task learning · Reinforcement learning · Task Analysis · Domain Adaptation and Few-Shot Learning · Intelligent Tutoring Systems and Adaptive Learning · Reinforcement Learning in Robotics

Tools

Open DOIOpen Access