Cloud software code generation via knowledge graphs and multi-modal learning

Abstract As cloud computing continues to experience rapid growth, the demand for cloud-native applications is escalating, leading to more complex and diverse development requirements. In this context, automated code generation plays a pivotal role in accelerating cloud-native application development...

Full description

Saved in:
Bibliographic Details
Main Authors: Fanlong Zhang, Huanming Chen, Quan Chen, Jianqi Liu
Format: Article
Language:English
Published: SpringerOpen 2025-07-01
Series:Journal of Cloud Computing: Advances, Systems and Applications
Subjects:
Online Access:https://doi.org/10.1186/s13677-025-00758-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238496545341440
author Fanlong Zhang
Huanming Chen
Quan Chen
Jianqi Liu
author_facet Fanlong Zhang
Huanming Chen
Quan Chen
Jianqi Liu
author_sort Fanlong Zhang
collection DOAJ
description Abstract As cloud computing continues to experience rapid growth, the demand for cloud-native applications is escalating, leading to more complex and diverse development requirements. In this context, automated code generation plays a pivotal role in accelerating cloud-native application development. However, existing studies often overlook the full potential of leveraging multiple program representations, typically focusing on a single form derived from well-structured programs. In this paper, we demonstrate that integrating multiple program representations, specifically, code snippets and their associated ASTs can significantly enhance code generation for cloud-native applications. We construct a code knowledge graph (CodeKG) to retrieve related programs based on textual and structural similarities, enabling richer contextual information for generation. To realize this integration, we design a framework that employs shared-retentive networks (shared-RetNet) and an AST-based Transformer to extract and align features from natural language, code tokens, and ASTs. By applying contrastive loss and cross-attention mechanisms, our method effectively fuses diverse modalities to strengthen code generation performance. Experiments on two processed open-source datasets demonstrate that our method, without relying on extensive pre-training, achieves superior results compared to existing pretrained models across BLEU-4, CodeBLEU, and ROUGE-L metrics, paving the way for more efficient and intelligent cloud-native software development.
format Article
id doaj-art-de5210d36c2047cbb0d25c356ddb9c68
institution Kabale University
issn 2192-113X
language English
publishDate 2025-07-01
publisher SpringerOpen
record_format Article
series Journal of Cloud Computing: Advances, Systems and Applications
spelling doaj-art-de5210d36c2047cbb0d25c356ddb9c682025-08-20T04:01:35ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2025-07-0114111910.1186/s13677-025-00758-5Cloud software code generation via knowledge graphs and multi-modal learningFanlong Zhang0Huanming Chen1Quan Chen2Jianqi Liu3School of Computer Science and Technology, Guangdong University of TechnologySchool of Computer Science and Technology, Guangdong University of TechnologySchool of Computer Science and Technology, Guangdong University of TechnologySchool of Computer Science and Technology, Guangdong University of TechnologyAbstract As cloud computing continues to experience rapid growth, the demand for cloud-native applications is escalating, leading to more complex and diverse development requirements. In this context, automated code generation plays a pivotal role in accelerating cloud-native application development. However, existing studies often overlook the full potential of leveraging multiple program representations, typically focusing on a single form derived from well-structured programs. In this paper, we demonstrate that integrating multiple program representations, specifically, code snippets and their associated ASTs can significantly enhance code generation for cloud-native applications. We construct a code knowledge graph (CodeKG) to retrieve related programs based on textual and structural similarities, enabling richer contextual information for generation. To realize this integration, we design a framework that employs shared-retentive networks (shared-RetNet) and an AST-based Transformer to extract and align features from natural language, code tokens, and ASTs. By applying contrastive loss and cross-attention mechanisms, our method effectively fuses diverse modalities to strengthen code generation performance. Experiments on two processed open-source datasets demonstrate that our method, without relying on extensive pre-training, achieves superior results compared to existing pretrained models across BLEU-4, CodeBLEU, and ROUGE-L metrics, paving the way for more efficient and intelligent cloud-native software development.https://doi.org/10.1186/s13677-025-00758-5Cloud computingSoftware engineeringCode generationMulti-modal learning
spellingShingle Fanlong Zhang
Huanming Chen
Quan Chen
Jianqi Liu
Cloud software code generation via knowledge graphs and multi-modal learning
Journal of Cloud Computing: Advances, Systems and Applications
Cloud computing
Software engineering
Code generation
Multi-modal learning
title Cloud software code generation via knowledge graphs and multi-modal learning
title_full Cloud software code generation via knowledge graphs and multi-modal learning
title_fullStr Cloud software code generation via knowledge graphs and multi-modal learning
title_full_unstemmed Cloud software code generation via knowledge graphs and multi-modal learning
title_short Cloud software code generation via knowledge graphs and multi-modal learning
title_sort cloud software code generation via knowledge graphs and multi modal learning
topic Cloud computing
Software engineering
Code generation
Multi-modal learning
url https://doi.org/10.1186/s13677-025-00758-5
work_keys_str_mv AT fanlongzhang cloudsoftwarecodegenerationviaknowledgegraphsandmultimodallearning
AT huanmingchen cloudsoftwarecodegenerationviaknowledgegraphsandmultimodallearning
AT quanchen cloudsoftwarecodegenerationviaknowledgegraphsandmultimodallearning
AT jianqiliu cloudsoftwarecodegenerationviaknowledgegraphsandmultimodallearning