Single Model Ensemble using Pseudo-Tags and Distinct Vectors

Ryosuke Kuwabara, Jun Suzuki, Hideki Nakayama

Research output: Contribution to journalArticlepeer-review

Abstract

Model ensemble techniques often increase task performance in neural networks; however, they require increased time, memory, and management effort. In this study, we propose a novel method that replicates the effects of a model ensemble with a single model. Our approach creates K-virtual models within a single parameter space using K-distinct pseudo-tags and K-distinct vectors. Experiments on text classification and sequence labeling tasks on several datasets demonstrate that our method emulates or outperforms a traditional model ensemble with 1/K-times fewer parameters.

Original languageEnglish
JournalUnknown Journal
Publication statusPublished - 2020 May 2

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Single Model Ensemble using Pseudo-Tags and Distinct Vectors'. Together they form a unique fingerprint.

Cite this