Ensemble of anchor adapters for transfer learning

Fuzhen Zhuang, Ping Luo, Sinno Jialin Pan, Hui Xiong, Qing He

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

In the past decade, there have been a large number of transfer learning algorithms proposed for various real-world applications. However, most of them are vulnerable to negative transfer1 since their performance is even worse than traditional supervised models. Aiming at more robust transfer learning models, we propose an ENsemble framework of anCHOR adapters (ENCHOR for short), in which an anchor adapter adapts the features of instances based on their similarities to a specif c anchor (i.e., a selected instance). Specif cally, the more similar to the anchor instance, the higher degree of the original feature of an instance remains unchanged in the adapted representation, and vice versa. This adapted representation for the data actually expresses the local structure around the corresponding anchor, and then any transfer learning method can be applied to this adapted representation for a prediction model, which focuses more on the neighborhood of the anchor. Next, based on multiple anchors, multiple anchor adapters can be built and combined into an ensemble for f nal output. Additionally, we develop an effective measure to select the anchors for ensemble building to achieve further performance improvement. Extensive experiments on hundreds of text classif cation tasks are conducted to demonstrate the effectiveness of ENCHOR. The results show that: when traditional supervised models perform poorly, ENCHOR (based on only 8 selected anchors) achieves 6% - 13% increase in terms of average accuracy compared with the state-of-the-art methods, and it greatly alleviates negative transfer.

Original languageEnglish (US)
Title of host publicationCIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages2335-2340
Number of pages6
ISBN (Electronic)9781450340731
DOIs
StatePublished - Oct 24 2016
Externally publishedYes
Event25th ACM International Conference on Information and Knowledge Management, CIKM 2016 - Indianapolis, United States
Duration: Oct 24 2016Oct 28 2016

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings
Volume24-28-October-2016

Conference

Conference25th ACM International Conference on Information and Knowledge Management, CIKM 2016
Country/TerritoryUnited States
CityIndianapolis
Period10/24/1610/28/16

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Business, Management and Accounting(all)

Fingerprint

Dive into the research topics of 'Ensemble of anchor adapters for transfer learning'. Together they form a unique fingerprint.

Cite this