Augmenting Transfer Learning with Semantic Reasoning

Freddy Lecue, Jiaoyan Chen, Jeff Z. Pan, Huajun Chen

Research output: Contribution to journalArticle

Abstract

Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements and what to transfer with semantic embeddings. We further present a general framework that integrates the above measurements and embeddings with existing transfer learning algorithms for higher performance. It has demonstrated to be robust in two real-world applications: bus delay forecasting and air quality forecasting.
Original languageEnglish
JournalarXiv
Publication statusSubmitted - 31 May 2019

Fingerprint

Semantics
Semantic Web
Air quality
Learning algorithms

Keywords

  • cs.LG
  • cs.AI
  • stat.ML

Cite this

Lecue, F., Chen, J., Pan, J. Z., & Chen, H. (2019). Augmenting Transfer Learning with Semantic Reasoning. Manuscript submitted for publication.

Augmenting Transfer Learning with Semantic Reasoning. / Lecue, Freddy; Chen, Jiaoyan; Pan, Jeff Z.; Chen, Huajun.

In: arXiv, 31.05.2019.

Research output: Contribution to journalArticle

Lecue, Freddy ; Chen, Jiaoyan ; Pan, Jeff Z. ; Chen, Huajun. / Augmenting Transfer Learning with Semantic Reasoning. In: arXiv. 2019.
@article{c477b27680cf4d02aebb94585ac07e64,
title = "Augmenting Transfer Learning with Semantic Reasoning",
abstract = "Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements and what to transfer with semantic embeddings. We further present a general framework that integrates the above measurements and embeddings with existing transfer learning algorithms for higher performance. It has demonstrated to be robust in two real-world applications: bus delay forecasting and air quality forecasting.",
keywords = "cs.LG, cs.AI, stat.ML",
author = "Freddy Lecue and Jiaoyan Chen and Pan, {Jeff Z.} and Huajun Chen",
note = "7 pages",
year = "2019",
month = "5",
day = "31",
language = "English",
journal = "arXiv",

}

TY - JOUR

T1 - Augmenting Transfer Learning with Semantic Reasoning

AU - Lecue, Freddy

AU - Chen, Jiaoyan

AU - Pan, Jeff Z.

AU - Chen, Huajun

N1 - 7 pages

PY - 2019/5/31

Y1 - 2019/5/31

N2 - Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements and what to transfer with semantic embeddings. We further present a general framework that integrates the above measurements and embeddings with existing transfer learning algorithms for higher performance. It has demonstrated to be robust in two real-world applications: bus delay forecasting and air quality forecasting.

AB - Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements and what to transfer with semantic embeddings. We further present a general framework that integrates the above measurements and embeddings with existing transfer learning algorithms for higher performance. It has demonstrated to be robust in two real-world applications: bus delay forecasting and air quality forecasting.

KW - cs.LG

KW - cs.AI

KW - stat.ML

M3 - Article

JO - arXiv

JF - arXiv

ER -