OntoZSL: Ontology-enhanced Zero-shot Learning

被引:34
|
作者
Geng, Yuxia [1 ]
Chen, Jiaoyan [2 ]
Chen, Zhuo [1 ]
Pan, Jeff Z. [3 ]
Ye, Zhiquan [4 ]
Yuan, Zonggang [5 ]
Jia, Yantao [6 ]
Chen, Huajun [7 ,8 ]
机构
[1] Zhejiang Univ, Hangzhou, Peoples R China
[2] Univ Oxford, Oxford, England
[3] Univ Edinburgh, Edinburgh, Midlothian, Scotland
[4] Zhejiang Univ, Coll Comp Sci, Hangzhou, Peoples R China
[5] Huawei Technol Co Ltd, NAIE CTO Off, Nanjing, Peoples R China
[6] Huawei Technol Co Ltd, Poisson Lab, Beijing, Peoples R China
[7] Zhejiang Univ, Coll Comp Sci, AZFT Knowledge Engine Lab, Hangzhou, Peoples R China
[8] Zhejiang Univ, HIC, AZFT Knowledge Engine Lab, Hangzhou, Peoples R China
关键词
Zero-shot Learning; Ontology; Generative Adversarial Networks; Image Classification; Knowledge Graph Completion; CLASSIFICATION;
D O I
10.1145/3442381.3450042
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Zero-shot Learning (ZSL), which aims to predict for those classes that have never appeared in the training data, has arisen hot research interests. The key of implementing ZSL is to leverage the prior knowledge of classes which builds the semantic relationship between classes and enables the transfer of the learned models (e.g., features) from training classes (i.e., seen classes) to unseen classes. However, the priors adopted by the existing methods are relatively limited with incomplete semantics. In this paper, we explore richer and more competitive prior knowledge to model the inter-class relationship for ZSL via ontology-based knowledge representation and semantic embedding. Meanwhile, to address the data imbalance between seen classes and unseen classes, we developed a generative ZSL framework with Generative Adversarial Networks (GANs). Our main findings include: (i) an ontology-enhanced ZSL framework that can be applied to different domains, such as image classification (IMGC) and knowledge graph completion (KGC); (ii) a comprehensive evaluation with multiple zero-shot datasets from different domains, where our method often achieves better performance than the state-of-the-art models. In particular, on four representative ZSL baselines of IMGC, the ontology-based class semantics outperform the previous priors e.g., the word embeddings of classes by an average of 12.4 accuracy points in the standard ZSL across two example datasets (see Figure 4).
引用
收藏
页码:3325 / 3336
页数:12
相关论文
共 50 条
  • [31] A review on multimodal zero-shot learning
    Cao, Weipeng
    Wu, Yuhao
    Sun, Yixuan
    Zhang, Haigang
    Ren, Jin
    Gu, Dujuan
    Wang, Xingkai
    WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2023, 13 (02)
  • [32] Zero-Shot Learning with Attribute Selection
    Guo, Yuchen
    Ding, Guiguang
    Han, Jungong
    Tang, Sheng
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 6870 - 6877
  • [33] Research and Development on Zero-Shot Learning
    Zhang L.-N.
    Zuo X.
    Liu J.-W.
    Zidonghua Xuebao/Acta Automatica Sinica, 2020, 46 (01): : 1 - 23
  • [34] Synthesizing Samples for Zero-shot Learning
    Guo, Yuchen
    Ding, Guiguang
    Han, Jungong
    Gao, Yue
    PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 1774 - 1780
  • [35] Towards Open Zero-Shot Learning
    Marmoreo, Federico
    Carrazco, Julio Ivan Davila
    Cavazza, Jacopo
    Murino, Vittorio
    IMAGE ANALYSIS AND PROCESSING, ICIAP 2022, PT II, 2022, 13232 : 564 - 575
  • [36] Zero-Shot Compositional Concept Learning
    Xu, Guangyue
    Kordjamshidi, Parisa
    Chai, Joyce Y.
    1ST WORKSHOP ON META LEARNING AND ITS APPLICATIONS TO NATURAL LANGUAGE PROCESSING (METANLP 2021), 2021, : 19 - 27
  • [37] Feature Enhanced Zero-Shot Stance Detection via Contrastive Learning
    Zhao, Xuechen
    Zou, Jiaying
    Zhang, Zhong
    Xie, Feng
    Zhou, Bin
    Tian, Lei
    PROCEEDINGS OF THE 2023 SIAM INTERNATIONAL CONFERENCE ON DATA MINING, SDM, 2023, : 900 - 908
  • [38] Semantic Autoencoder for Zero-Shot Learning
    Kodirov, Elyor
    Xiang, Tao
    Gong, Shaogang
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 4447 - 4456
  • [39] Variational Disentangle Zero-Shot Learning
    Su, Jie
    Wan, Jinhao
    Li, Taotao
    Li, Xiong
    Ye, Yuheng
    MATHEMATICS, 2023, 11 (16)
  • [40] Prototype rectification for zero-shot learning
    Yi, Yuanyuan
    Zeng, Guolei
    Ren, Bocheng
    Yang, Laurence T.
    Chai, Bin
    Li, Yuxin
    PATTERN RECOGNITION, 2024, 156