Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

Abstract

Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and program repair. They benefit from leveraging program structure like control flow graphs, but they are not well-suited to tasks like program execution that require far more sequential reasoning steps than number of GNN propagation steps. Recurrent neural networks (RNNs), on the other hand, are well-suited to long sequential chains of reasoning, but they do not naturally incorporate program structure and generally perform worse on the above tasks. Our aim is to achieve the best of both worlds, and we do so by introducing a novel GNN architecture, the Instruction Pointer Attention Graph Neural Networks (IPA-GNN), which achieves improved systematic generalization on the task of learning to execute programs using control flow graphs. The model arises by considering RNNs operating on program traces with branch decisions as latent variables. The IPA-GNN can be seen either as a continuous relaxation of the RNN model or as a GNN variant more tailored to execution. To test the models, we propose evaluating systematic generalization on learning to execute using control flow graphs, which tests sequential reasoning and use of program structure. More practically, we evaluate these models on the task of learning to execute partial programs, as might arise if using the model as a heuristic function in program synthesis. Results show that the IPA-GNN outperforms a variety of RNN and GNN baselines on both tasks.

arXiv commentAccepted at NeurIPS 2020

References in corpus (11)

• Sequence to Sequence Learning with Neural Networks
• Gated Graph Sequence Neural Networks
• Neural Programmer-Interpreters
• Neural GPUs Learn Algorithms
• Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
• Learning to Transduce with Unbounded Memory
• Relational Graph Attention Networks
• Making Neural Programming Architectures Generalize via Recursion
• LambdaNet: Probabilistic Type Inference using Graph Neural Networks
• Differentiable Programs with Neural Libraries
• Inferring Javascript types using Graph Neural Networks

Cited by in corpus (5)

• ProTo: Program-Guided Transformer for Program-Guided Tasks
• A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration
• Learning to Extend Program Graphs to Work-in-Progress Code
• Meta-Learning an Inference Algorithm for Probabilistic Programs
• Reinforcement Learning of Implicit and Explicit Control Flow in Instructions