Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learning to Forget for Meta-Learning

About

Few-shot learning is a challenging problem where the goal is to achieve generalization from only few examples. Model-agnostic meta-learning (MAML) tackles the problem by formulating prior knowledge as a common initialization across tasks, which is then used to quickly adapt to unseen tasks. However, forcibly sharing an initialization can lead to conflicts among tasks and the compromised (undesired by tasks) location on optimization landscape, thereby hindering the task adaptation. Further, we observe that the degree of conflict differs among not only tasks but also layers of a neural network. Thus, we propose task-and-layer-wise attenuation on the compromised initialization to reduce its influence. As the attenuation dynamically controls (or selectively forgets) the influence of prior knowledge for a given task and each layer, we name our method as L2F (Learn to Forget). The experimental results demonstrate that the proposed method provides faster adaptation and greatly improves the performance. Furthermore, L2F can be easily applied and improve other state-of-the-art MAML-based frameworks, illustrating its simplicity and generalizability.

Sungyong Baik, Seokil Hong, Kyoung Mu Lee• 2019

Related benchmarks

TaskDatasetResultRank
5-way Few-shot ClassificationMini-Imagenet (test)
1-shot Accuracy62.12
141
5-way Few-shot ClassificationminiImageNet standard (test)
Accuracy69.38
91
Few-shot Image ClassificationtieredImageNet (test)
Accuracy73.34
86
Showing 3 of 3 rows

Other info

Follow for update