Call Me Maybe: Enhancing JavaScript Call Graph Construction using Graph Neural Networks

2025-06-22

AI Summary

JavaScript’s dynamic features render existing call graph construction methods neither sound nor complete, often introducing spurious edges or missing genuine calls. To address this, we propose the first GNN-based link prediction framework for multi-file, whole-program graphs, formulating unresolved call site resolution as a heterogeneous edge link prediction task on program graphs. Our approach innovatively integrates syntactic and semantic edges to construct richer program representations, jointly leverages static and dynamic call edges as weak supervision signals, and supports cross-project knowledge transfer. Evaluated on 50 widely used JavaScript libraries, our method achieves 42.3% top-1 accuracy in identifying the correct target function for unresolved call sites, with 72.1% of ground-truth targets ranked within the top five candidates. This substantially improves call graph precision and significantly reduces manual verification effort.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Static analysis plays a key role in finding bugs, including security issues. A critical step in static analysis is building accurate call graphs that model function calls in a program. However, due to hard-to-analyze language features, existing call graph construction algorithms for JavaScript are neither sound nor complete. Prior work shows that even advanced solutions produce false edges and miss valid ones. In this work, we assist these tools by identifying missed call edges. Our main idea is to frame the problem as link prediction on full program graphs, using a rich representation with multiple edge types. Our approach, GRAPHIA, leverages recent advances in graph neural networks to model non-local relationships between code elements. Concretely, we propose representing JavaScript programs using a combination of syntactic- and semantic-based edges. GRAPHIA can learn from imperfect labels, including static call edges from existing tools and dynamic edges from tests, either from the same or different projects. Because call graphs are sparse, standard machine learning metrics like ROC are not suitable. Instead, we evaluate GRAPHIA by ranking function definitions for each unresolved call site. We conduct a large-scale evaluation on 50 popular JavaScript libraries with 163K call edges (150K static and 13K dynamic). GRAPHIA builds program graphs with 6.6M structural and 386K semantic edges. It ranks the correct target as the top candidate in over 42% of unresolved cases and within the top 5 in 72% of cases, reducing the manual effort needed for analysis. Our results show that learning-based methods can improve the recall of JavaScript call graph construction. To our knowledge, this is the first work to apply GNN-based link prediction to full multi-file program graphs for interprocedural analysis.

Problem

• Improving JavaScript call graph accuracy using GNNs
• Addressing false and missing edges in static analysis
• Enhancing interprocedural analysis with multi-file program graphs

Innovation

• Uses Graph Neural Networks for call edge prediction
• Combines syntactic and semantic edges in program graphs
• Learns from both static and dynamic call edges