SupplementaryMaterialof TowardsEnablingMeta-Learning fromTargetModels
–Neural Information Processing Systems
In this experiment, we modify ProtoNet slightly to fit regression problem. In detail, we try to meta-learn an embedding functionφ: R R100, with assistance of which the similarity-based regressionmodelg(;{φ(xi)|(xi,yi) S})workswellacrossalltasks.
Neural Information Processing Systems
Feb-8-2026, 09:55:56 GMT