Meta-Learning for Medium-shot Sparse Learning via Deep Kernels
| Autor: | Zohreh Adabi Firuzjaee, Sayed Kamaledin Ghiasi-Shirazi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | Computer and Knowledge Engineering, Vol 5, Iss 2, Pp 45-56 (2022) |
| Druh dokumentu: | article |
| ISSN: | 2538-5453 2717-4123 |
| DOI: | 10.22067/cke.2022.77529.1060 |
| Popis: | Few-shot learning assumes that we have a very small dataset for each task and trains a model on the set of tasks. For real-world problems, however, the amount of available data is substantially much more; we call this a medium-shot setting, where the dataset often has several hundreds of data. Despite their high accuracy, deep neural networks have a drawback as they are black-box. Learning interpretable models has become more important over time. This study aims to obtain sample-based interpretability using the attention mechanism. The main idea is reducing the task training data into a small number of support vectors using sparse kernel methods, and the model then predicts the test data of the task based on these support vectors. We propose a sparse medium-shot learning algorithm based on a metric-based Bayesian meta-learning algorithm whose output is probabilistic. Sparsity, along with uncertainty, effectively plays a key role in interpreting the model's behavior. In our experiments, we show that the proposed method provides significant interpretability by selecting a small number of support vectors and, at the same time, has a competitive accuracy compared to other less interpretable methods. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|