Informed Plastic Attractors for Adaptive Few-Shot Learning

Hebbian plasticity enables gradient-free adaptation at deployment, making it attractive for few-shot and continual learning, but designing plasticity rules typically requires black-box optimization because their weight dynamics are not well understood. We introduce $\text{Informed Plastic Attractors}$ (IPA) that analytically define Hebbian plasticity matrices ($\mathbf{ABCD}$) in correspondence with the Information Bottleneck principle, resulting in unique local weight attractors. From $K$ labeled shots, these attractors adapt the head on a stream of single unlabeled data without gradients, replay or a query batch. We formalise a unique, locally contractive fixed point of the expected centroid mode and sample-wise dissipation of pre-activation energy. Under matched unlabeled-data access, IPA matches or improves nearest-class-mean classifiers, with gains where prototypes are weak, while batch-transductive methods win only with large, balanced query pools; the same plastic head meta-trains bodies that transfer across domains and heads; and in few-shot class-incremental learning with a frozen ResNet-12 it outperforms NCM-r, TENT, TIM, TEEN, ER, and the published NC-FSCIL result on CIFAR-100 without replay or gradient updates, is never below the prototype baseline, and with a frozen DINO backbone ends at $84.04\%$ final-session accuracy on MiniImageNet against $78.17\%$ for ER.