TY - JOUR
T1 - Benchmarking knowledge-driven zero-shot learning
AU - Geng, Yuxia
AU - Chen, Jiaoyan
AU - Zhuang, Xiang
AU - Chen, Zhuo
AU - Pan, Jeff Z.
AU - Li, Juan
AU - Yuan, Zonggang
AU - Chen, Huajun
N1 - Funding Information:
This work is partially funded by NSFCU19B2027/91846204, the EPSRC project ConCur (EP/V050869/1) and the Chang Jiang Scholars Program ( J2019032 ).
Publisher Copyright:
© 2022 Elsevier B.V.
PY - 2023/1/1
Y1 - 2023/1/1
N2 - 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 a few classic and state-of-the-art methods for each task, including a method with KG augmented explanation. 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.
AB - 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 a few classic and state-of-the-art methods for each task, including a method with KG augmented explanation. 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.
KW - Zero-shot learning
KW - Knowledge Graph
KW - Image classification
KW - Relation extraction
KW - Knowledge Graph completion
KW - Ontology
KW - Semantic embedding
U2 - 10.1016/j.websem.2022.100757
DO - 10.1016/j.websem.2022.100757
M3 - Article
VL - 75
JO - Journal of Web Semantics
JF - Journal of Web Semantics
SN - 1570-8268
M1 - 100757
ER -