Benchmarking Knowledge-driven Zero-shot Learning release_vfe4vdxlprcrtpcjshda7ofxtu

by Yuxia Geng, Jiaoyan Chen, Xiang Zhuang, Zhuo Chen, Jeff Z. Pan, Juan Li, Zonggang Yuan, Huajun Chen

Released as a article .

2021  

Abstract

External knowledge (a.k.a. side information) plays a critical role in zero-shot learning (ZSL) which aims to predict with unseen classes that have never appeared in training data. Several kinds of external knowledge, such as text and attribute, have been widely investigated, but they alone are limited with incomplete semantics. Some very recent studies thus propose to use Knowledge Graph (KG) due to its high expressivity and compatibility for representing kinds of knowledge. However, the ZSL community is still in short of standard benchmarks for studying and comparing different external knowledge settings and different KG-based ZSL methods. In this paper, we proposed six resources covering three tasks, i.e., zero-shot image classification (ZS-IMGC), zero-shot relation extraction (ZS-RE), and zero-shot KG completion (ZS-KGC). Each resource has a normal ZSL benchmark and a KG containing semantics ranging from text to attribute, from relational knowledge to logical expressions. We have clearly presented these resources including their construction, statistics, data formats and usage cases w.r.t. different ZSL methods. More importantly, we have conducted a comprehensive benchmarking study, with two general and state-of-the-art methods, two setting-specific methods and one interpretable method. We discussed and compared different ZSL paradigms w.r.t. different external knowledge settings, and found that our resources have great potential for developing more advanced ZSL methods and more solutions for applying KGs for augmenting machine learning. All the resources are available at https://github.com/China-UK-ZSL/Resources_for_KZSL.
In text/plain format

Archived Files and Locations

application/pdf  4.3 MB
file_47aswny33fd6zlrqj3k4pniblu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-11-11
Version   v2
Language   en ?
arXiv  2106.15047v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 455511b7-a290-494c-a16e-9d042ddc2f28
API URL: JSON