DPEfficR: a data and parameter efficient approach for training neural API recommendation model

Recommending application programming interfaces (APIs) is practical and essential in today’s programming landscape. An accurate API recommendation system could significantly improve developers’ coding efficiency. State-of-the-art (SOTA) API recommendation systems typically employ deep learning model...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Automated software engineering Ročník 32; číslo 2; s. 64
Hlavní autoři: Yu, Haibo, Han, Xiaohong, Chen, Simin, Feng, Xiaoning, Sun, Guangzhao, Yang, Wei
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.11.2025
Springer Nature B.V
Témata:
Ablation
Accuracy
Application programming interface
Artificial Intelligence
Computer Science
Datasets
Deep learning
Effectiveness
Efficiency
Labeling
Language
Large language models
Methods
Modules
Natural language
Parameters
Queries
Recommender systems
Run time (computers)
Semantics
Software Engineering/Programming and Operating Systems
Tuning
Use statistics
Data and parameter efficient
API recommendation
ISSN:0928-8910, 1573-7535
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recommending application programming interfaces (APIs) is practical and essential in today’s programming landscape. An accurate API recommendation system could significantly improve developers’ coding efficiency. State-of-the-art (SOTA) API recommendation systems typically employ deep learning models as the backend model. However, training the backend deep learning model for API recommendation systems poses a challenging task due to the significant effort required for data labeling and the need for extensive computations. These challenges deeply affect the process of updating an existing API recommendation system when the API evolves. To address these issues, this paper proposes DPEfficR , a data and parameter efficient method for building API recommendation systems. Specifically, DPEfficR includes (1) the data selection module; (2) the task-specific parameter tuning module; and (3) the runtime API selection module. The data selection module selects representative data, while the task-specific parameter tuning module tunes pre-trained LLMs with a small number of parameters. Once the LLM is well-tuned, the runtime API selection module searches for a more accurate API sequence through consistency checking. We compare our approach against seven baseline methods, which belong to three different types. Our comprehensive evaluation demonstrates the effectiveness of our approach in recommending a more accurate API sequence, achieving improvements of 40% in BLEU-4 and 25% in ROUGE-2 over the baseline methods, with only tunable parameters, representing just 0.049% of the parameters used in the baseline methods. Moreover, our ablation study demonstrates the effectiveness of the proposed modules in our systems.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0928-8910
1573-7535
DOI:10.1007/s10515-025-00530-8