• Home
  • Search
  • Transductive zero-shot learning via knowledge graph and graph convolutional networks.
  • Cite Icon2
  • https://doi.org/10.1038/s41598-025-13612-0Copy DOI Icon

Transductive zero-shot learning via knowledge graph and graph convolutional networks.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Zero-shot learning methods are used to recognize objects of unseen categories. By transferring knowledge from the seen classes to describe the unseen classes, deep learning models can recognize unseen categories. However, relying solely on a small labeled seen dataset and the limited semantic relationships will lead to a significant domain shift, hindering the classification performance. To tackle this problem, we propose a transductive zero-shot learning method, based on Knowledge Graph and Graph Convolutional Network. We firstly learn a knowledge graph, where each node represents a category encoded by its semantic embedding. With a shallow graph convolutional network having a small number of layers, we learn the classifier for each category, supervised by the visual classifiers of the seen categories. During testing, a clustering strategy, the Double Filter Module with Hungarian algorithm, is applied to the unseen samples, and then, the learned classifiers are used to predict their categories. Pseudo annotations are given to the samples that are more accurately classified. In the transductive setting, the unseen categories with higher classification accuracy are assigned pseudo annotations, and can be associated with the seen categories to progressively update model parameters. We validate the proposed model on three data sets, and our model outperforms other state-of-the-art methods, achieving 47.36% accuracy on AWA2, 30.69% on ImageNet50, and 18.87 on ImageNet100, with a 4-10% improvement over existing methods.

Similar Papers
  • PDF
  • Research Article
  • Citations7

Improved Collaborative Recommendation Model: Integrating Knowledge Embedding and Graph Contrastive Learning

  • Oct 13, 2023
  • Electronics
  • Liwei Jiang +3
  • Research Article
  • Citations47

Investigating the Bilateral Connections in Generative Zero-Shot Learning.

  • Feb 02, 2021
  • IEEE Transactions on Cybernetics
  • Jingjing Li +4
  • Research Article
  • Citations14

Benchmarking knowledge-driven zero-shot learning

  • Sep 17, 2022
  • Journal of Web Semantics
  • Yuxia Geng +7
  • Conference Article
  • Citations12

Fault Classification of Industrial Processes based on Generalized Zero-Shot Learning

  • May 14, 2021
  • Jiacheng Huang +3
  • Research Article
  • Citations67

Zero-Shot and Few-Shot Learning With Knowledge Graphs: A Comprehensive Survey

  • Jun 01, 2023
  • Proceedings of the IEEE
  • Jiaoyan Chen +7
  • Conference Article

An Efficient Recommendation Algorithm Integrating Knowledge Graph with Graph Convolutional Networks

  • Feb 01, 2023
  • Changzheng Xing +2
  • Research Article
  • Citations17

Learnable convolutional attention network for knowledge graph completion

  • Jan 03, 2024
  • Knowledge-Based Systems
  • Bin Shang +2
  • Conference Article
  • Citations8

Knowledge Graph for Power Grid Dispatching of Digital Homes based on Graph Convolutional Network

  • Sep 01, 2020
  • Fei Peng +5
  • Book Chapter
  • Citations11

Personalized Recommendation of English Learning Based on Knowledge Graph and Graph Convolutional Network

  • Jan 01, 2021
  • Yuan Sun +2
  • Conference Article
  • Citations2

A Zero-shot Learning Method with a Multi-Modal Knowledge Graph

  • Oct 01, 2022
  • Yuhong Zhang +3
  • Conference Article
  • Citations15

Residual Graph Convolutional Networks for Zero-Shot Learning

  • Dec 15, 2019
  • Jiwei Wei +5
  • Research Article
  • Citations8

Aspect-level sentiment analysis merged with knowledge graph and graph convolutional neural network

  • Nov 01, 2021
  • Journal of Physics: Conference Series
  • Zuhua Dai +3
  • Research Article
  • Citations20

Bidirectional generative transductive zero-shot learning

  • Sep 12, 2020
  • Neural Computing and Applications
  • Xinpeng Li +5
  • PDF
  • Research Article
  • Citations11

Semantic embeddings of generic objects for zero-shot learning

  • Jan 15, 2019
  • EURASIP Journal on Image and Video Processing
  • Tristan Hascoet +2
  • Conference Article
  • Citations20

Zero-Shot Learning via Contrastive Learning on Dual Knowledge Graphs

  • Oct 01, 2021
  • Jin Wang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.