Improved Meta-learning by Parameter Adjustment via Latent Variables and Probabilistic Inference

• SHIMIZU Eiki

  Waseda University

• AOKI Shogo

  Waseda University

• MIKAWA Kenta

  Shonan Institute of Technology

• GOTO Masayuki

  Waseda University

Bibliographic Information

Other Title

• 潜在変数を導入したパラメータ調整に基づくメタ学習法の改良法

Abstract

Standard deep neural networks require large training data and fail to achieve good performance in the small data regime. To overcome this limitation, meta-learning approaches have recently been explored. The goal of meta-learning methods is to empower models to automatically learn across-task knowledge usually referred to meta-knowledge, so that task-specific knowledge of new tasks can be obtained using only few data. Among them, Model-Agnostic Meta-Learning or MAML is one of the best approaches, showing high performances in many settings. However, MAML does not consider varying effectiveness of meta-knowledge to each task, since learning rate is set constant across tasks. In this paper, we propose a model that adjusts learning rate for each task by introducing latent variables and applying probabilistic inference. We demonstrate that this approach improves the performance of MAML on few-shot image classification benchmark dataset, and confirm that learning rate is adaptively adjusted by visualizing latent variables.

Journal

• Proceedings of the Annual Conference of JSAI

  Proceedings of the Annual Conference of JSAI JSAI2020 (0), 4I3GS202-4I3GS202, 2020

  The Japanese Society for Artificial Intelligence

Keywords

• Meta Learning
• Image Recognition
• Deep Learning

Details

• CRID: 1390566775143095296
• NII Article ID: 130007857364
• DOI: 10.11517/pjsai.jsai2020.0_4i3gs202
• Text Lang: ja
• Data Source:
  • JaLC
  • CiNii Articles
• Abstract License Flag: Disallowed