Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
This work addresses the challenge of efficiently leveraging prior knowledge for new tasks in few-shot learning, offering a novel approach with demonstrated performance gains.
The paper tackled the problem of transferring knowledge between tasks in few-shot learning by proposing an asymmetric affinity score based on maximum bipartite matching and Fisher Information, which improved classification accuracy over state-of-the-art methods on benchmark datasets.
We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one. Our method is based on the maximum bipartite matching algorithm and utilizes the Fisher Information matrix. We provide theoretical analyses demonstrating that the proposed score is mathematically well-defined, and subsequently use the affinity score to propose a novel algorithm for the few-shot learning problem. In particular, using this score, we find relevant training data labels to the test data and leverage the discovered relevant data for episodically fine-tuning a few-shot model. Results on various few-shot benchmark datasets demonstrate the efficacy of the proposed approach by improving the classification accuracy over the state-of-the-art methods even when using smaller models.