Label Propagation Adaptive Resonance Theory for Semi-supervised Continuous Learning
This addresses the challenge of semi-supervised continuous learning for AI systems in real-world scenarios with scarce labels, though it appears incremental as it builds on existing paradigms.
The paper tackles the problem of learning from limited labeled data in a continuous setting by proposing LPART, which uses online label propagation to improve classification accuracy as more data is observed, achieving higher accuracies on visual and audio datasets when both labeled and unlabeled data are used.
Semi-supervised learning and continuous learning are fundamental paradigms for human-level intelligence. To deal with real-world problems where labels are rarely given and the opportunity to access the same data is limited, it is necessary to apply these two paradigms in a joined fashion. In this paper, we propose Label Propagation Adaptive Resonance Theory (LPART) for semi-supervised continuous learning. LPART uses an online label propagation mechanism to perform classification and gradually improves its accuracy as the observed data accumulates. We evaluated the proposed model on visual (MNIST, SVHN, CIFAR-10) and audio (NSynth) datasets by adjusting the ratio of the labeled and unlabeled data. The accuracies are much higher when both labeled and unlabeled data are used, demonstrating the significant advantage of LPART in environments where the data labels are scarce.