Generative Continual Concept Learning
This work addresses the problem of catastrophic forgetting in continual learning for AI systems, offering a method to efficiently adapt concepts to new domains, though it appears incremental as it builds on existing theories like Parallel Distributed Processing.
The paper tackles the challenge of continual concept learning in AI, where models struggle to generalize learned concepts to new domains without forgetting past knowledge, by developing a computational model that expands concepts to new domains using few labeled samples and generates pseudo-data to prevent catastrophic forgetting.
After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for current Artificial Intelligence algorithms as persistent model retraining is necessary. Inspired by the Parallel Distributed Processing learning and the Complementary Learning Systems theories, we develop a computational model that is able to expand its previously learned concepts efficiently to new domains using a few labeled samples. We couple the new form of a concept to its past learned forms in an embedding space for effective continual learning. Doing so, a generative distribution is learned such that it is shared across the tasks in the embedding space and models the abstract concepts. This procedure enables the model to generate pseudo-data points to replay the past experience to tackle catastrophic forgetting.