Skip to main content
Kent Academic Repository

Contrastive Learning with Heterogeneous Graph Attention Networks on Short Text Classification

Sun, Zhongtian, Harit, Anoushka, Cristea, Alexandra I., Yu, Jialin, Shi, Lei, Al Moubayed, Noura (2022) Contrastive Learning with Heterogeneous Graph Attention Networks on Short Text Classification. In: International Joint Conference on Neural Networks (IJCNN), 18-23 July 2022, Padua, Italy. (doi:10.1109/IJCNN55064.2022.9892257) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:108671)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL:
https://doi.org/10.1109/IJCNN55064.2022.9892257

Abstract

Graph neural networks (GNNs) have attracted extensive interest in text classification tasks due to their expected superior performance in representation learning. However, most existing studies adopted the same semi-supervised learning setting as the vanilla Graph Convolution Network (GCN), which requires a large amount of labelled data during training and thus is less robust when dealing with large-scale graph data with fewer labels. Additionally, graph structure information is normally captured by direct information aggregation via network schema and is highly dependent on correct adjacency information. Therefore, any missing adjacency knowledge may hinder the performance. Addressing these problems, this paper thus proposes a novel method to learn a graph structure, NC-HGAT, by expanding a state-of-the-art self-supervised heterogeneous graph neural network model (HGAT) with simple neighbour contrastive learning. The new NC-HGAT considers the graph structure information from heterogeneous graphs with multilayer perceptrons (MLPs) and delivers consistent results, despite the corrupted neighbouring connections. Extensive experiments have been implemented on four benchmark short-text datasets. The results demonstrate that our proposed model NC-HGAT significantly outperforms state-of-the-art methods on three datasets and achieves competitive performance on the remaining dataset.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.1109/IJCNN55064.2022.9892257
Subjects: Q Science > Q Science (General) > Q335 Artificial intelligence
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Zhongtian Sun
Date Deposited: 06 Feb 2025 16:04 UTC
Last Modified: 10 Feb 2025 17:24 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/108671 (The current URI for this page, for reference purposes)

University of Kent Author Information

  • Depositors only (login required):

Total unique views of this page since July 2020. For more details click on the image.