Ontology-Driven Cross-Domain Transfer Learning

Mattia Fumagalli, Gábor Bella, Samuele Conti, Fausto Giunchiglia
{"title":"Ontology-Driven Cross-Domain Transfer Learning","authors":"Mattia Fumagalli, Gábor Bella, Samuele Conti, Fausto Giunchiglia","doi":"10.3233/faia200676","DOIUrl":null,"url":null,"abstract":"The aim of transfer learning is to reuse learnt knowledge across different contexts. In the particular case of cross-domain transfer (also known as domain adaptation), reuse happens across different but related knowledge domains. While there have been promising first results in combining learning with symbolic knowledge to improve cross-domain transfer results, the singular ability of ontologies for providing classificatory knowledge has not been fully exploited so far by the machine learning community. We show that ontologies, if properly designed, are able to support transfer learning by improving generalization and discrimination across classes. We propose an architecture based on direct attribute prediction for combining ontologies with a transfer learning framework, as well as an ontology-based solution for cross-domain generalization based on the integration of top-level and domain ontologies. We validate the solution on an experiment over an image classification task, demonstrating the system’s improved classification performance.","PeriodicalId":90829,"journal":{"name":"Formal ontology in information systems : proceedings of the ... International Conference. FOIS (Conference)","volume":"15 1","pages":"249-263"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Formal ontology in information systems : proceedings of the ... International Conference. FOIS (Conference)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3233/faia200676","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

The aim of transfer learning is to reuse learnt knowledge across different contexts. In the particular case of cross-domain transfer (also known as domain adaptation), reuse happens across different but related knowledge domains. While there have been promising first results in combining learning with symbolic knowledge to improve cross-domain transfer results, the singular ability of ontologies for providing classificatory knowledge has not been fully exploited so far by the machine learning community. We show that ontologies, if properly designed, are able to support transfer learning by improving generalization and discrimination across classes. We propose an architecture based on direct attribute prediction for combining ontologies with a transfer learning framework, as well as an ontology-based solution for cross-domain generalization based on the integration of top-level and domain ontologies. We validate the solution on an experiment over an image classification task, demonstrating the system’s improved classification performance.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
本体驱动的跨领域迁移学习
迁移学习的目的是在不同的语境中重复使用所学的知识。在跨领域转移(也称为领域适应)的特殊情况下,重用发生在不同但相关的知识领域之间。虽然在将学习与符号知识相结合以改善跨领域迁移结果方面已经取得了有希望的初步成果,但到目前为止,机器学习社区尚未充分利用本体提供分类知识的单一能力。我们表明,如果设计得当,本体能够通过提高跨类的泛化和区分来支持迁移学习。我们提出了一种基于直接属性预测的本体与迁移学习框架相结合的体系结构,以及一种基于顶层本体和领域本体集成的跨域泛化解决方案。我们在一个图像分类任务的实验中验证了该解决方案,证明了系统的分类性能得到了提高。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Fiat Surfaces in the Basic Formal Ontology. Axiomatizing SNOMED CT Disorders: Should There Be Room for Interpretation? Asymmetric Hybrids: Dialogues for Computational Concept Combination Debugging Classical Ontologies Using Defeasible Reasoning Tools Towards a Unified Dispositional Framework for Realizable Entities
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1