Text

Heterogeneous Few-Shot Model Rectification With Semantic Mapping

There still involve lots of challenges when applying machine learning algorithms in unknown environments, especially those with limited training data. To handle the data insufficiency and make a further step towards robust learning, we adopt the learnware notion Z.-H. Zhou, “Learnware: On the future of machine learning,” Front. Comput. Sci. , vol. 10, no. 4 pp. 589–590, 2016 which equips a model with an essential reusable property—the model learned in a related task could be easily adapted to the current data-scarce environment without data sharing . To this end, we propose the REctiFy via heterOgeneous pRedictor Mapping ( ReForm ) framework enabling the current model to take advantage of a related model from two kinds of heterogeneous environment , i.e., either with different sets of features or labels. By Encoding Meta InformaTion ( Emit ) of features and labels as the model specification, we utilize an optimal transported semantic mapping to characterize and bridge the environment changes. After fine-tuning over a few labeled examples through a biased regularization objective, the transformed heterogeneous model adapts to the current task efficiently. We apply ReForm over both synthetic and real-world tasks such as few-shot image classification with either learned or pre-defined specifications. Experimental results validate the effectiveness and practical utility of the proposed ReForm framework.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.43 No.11 November 2021

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 3878-3891

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

TRANSFER LEARNING
MODEL REUSE
FEW-SHOT LEARNING
HETEROGENEOUS MODEL REUSE
META REPRESENTATION
LEARNWARE

Info Detail Spesifik

10.1109/TPAMI.2020.2994749

Pernyataan Tanggungjawab

Han-Jia Ye, De-Chuan Zhan, Yuan Jiang, Zhi-Hua Zhou

Versi lain/terkait

Lampiran Berkas

Komentar