Distribution Embedding Network for Meta-Learning with Variable-Length Input

Lang Liu, Mahdi Milani Fard, Sen Zhao

Keywords: meta-learning, variable-length input, distribution embedding

Abstract: We propose Distribution Embedding Network (DEN) for meta-learning, which is designed for applications where both the distribution and the number of features could vary across tasks. DEN first transforms features using a learned piecewise linear function, then learns an embedding of the underlying data distribution after the transformation, and finally classifies examples based on the distribution embedding. We show that the parameters of the distribution embedding and the classification modules can be shared across tasks. We propose a novel methodology to mass-simulate binary classification training tasks, and demonstrate that DEN outperforms existing methods in a number of test tasks in numerical studies.

One-sentence Summary: In this paper we propose Distribution Embedding Network for meta-learning, which is designed for applications where both the distribution and the number of features could vary across tasks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=223ALQsu2a