Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Abstract

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies

Date
Dec 14, 2022 12:00 PM — 12:30 PM
Location
Online (Zoom)
Chia-Cheng Kuo
Chia-Cheng Kuo
Graduate Research Assistant

I’m a master student studying Computer Engineering (Computer Systems Specialization) in Arizona State University, Tempe. Currently working on research projects in Embedded Machine Intelligence Lab (EMIL) under the supervision of Dr. Hassan Ghasemzadeh.