Article: HITT: heterogeneous imbalance-text transformer for web service representation Journal: International Journal of Web and Grid Services (IJWGS) 2026 Vol.22 No.1 pp.63 - 89 Abstract: The explosive growth of web services complicates developer selection. While service representation is key for intelligent management, existing methods rely on textual semantics or network structure alone, often neglecting deep multi-feature fusion and text imbalance or absence across nodes. This paper proposes a transformer model empowered by heterogeneous networks to unify context-aware text and heterogeneous structure encoding. Heterogeneous structure information is incorporated into each transformer layer to capture node/edge information, handling nodes with or without text. A fully-connected attention mechanism integrates representations from text-rich neighbours, textless neighbours, and the node's own content at each layer. To fully fuse features, a specialised transformation matrix projects different node types into a shared latent space. Experiments show our method outperforms the strongest baselines by nearly 1% in LogLoss and 2% in AUC. Inderscience Publishers - linking academia, business and industry through research

Title: HITT: heterogeneous imbalance-text transformer for web service representation

Authors: Kang Guosheng; Feng Jianhua; Xiao Yong; Liu Jianxun; Cao Buqing

Addresses: School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan City, Hunan Province, China ' School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan City, Hunan Province, China ' School of Computer Science and Artificial Intelligence, HuaiHua University, HuaiHua City, Hunan Province, China ' School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan City, Hunan Province, China ' School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan City, Hunan Province, China

Abstract: The explosive growth of web services complicates developer selection. While service representation is key for intelligent management, existing methods rely on textual semantics or network structure alone, often neglecting deep multi-feature fusion and text imbalance or absence across nodes. This paper proposes a transformer model empowered by heterogeneous networks to unify context-aware text and heterogeneous structure encoding. Heterogeneous structure information is incorporated into each transformer layer to capture node/edge information, handling nodes with or without text. A fully-connected attention mechanism integrates representations from text-rich neighbours, textless neighbours, and the node's own content at each layer. To fully fuse features, a specialised transformation matrix projects different node types into a shared latent space. Experiments show our method outperforms the strongest baselines by nearly 1% in LogLoss and 2% in AUC.

Keywords: web service; representation learning; service recommendation; service classification; heterogeneous network.

DOI: 10.1504/IJWGS.2026.151907

International Journal of Web and Grid Services, 2026 Vol.22 No.1, pp.63 - 89

Received: 12 Nov 2024
Accepted: 11 Dec 2025
Published online: 25 Feb 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: HITT: heterogeneous imbalance-text transformer for web service representation

Keep up-to-date