Evaluation of Generalizability of Neural Program Analyzers under Semantic-Preserving Transformations

• URL: http://arxiv.org/abs/2004.07313v2
• Date: Thu, 18 Mar 2021 07:10:31 GMT
• Title: Evaluation of Generalizability of Neural Program Analyzers under Semantic-Preserving Transformations
• Authors: Md Rafiqul Islam Rabin, Mohammad Amin Alipour
• Abstract summary: We evaluate the generalizability of two popular neural program analyzers using seven semantically-equivalent transformations of programs. Our results caution that in many cases the neural program analyzers fail to generalize well, sometimes to programs with negligible textual differences.
• Score: 1.3477892615179483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The abundance of publicly available source code repositories, in conjunction with the advances in neural networks, has enabled data-driven approaches to program analysis. These approaches, called neural program analyzers, use neural networks to extract patterns in the programs for tasks ranging from development productivity to program reasoning. Despite the growing popularity of neural program analyzers, the extent to which their results are generalizable is unknown. In this paper, we perform a large-scale evaluation of the generalizability of two popular neural program analyzers using seven semantically-equivalent transformations of programs. Our results caution that in many cases the neural program analyzers fail to generalize well, sometimes to programs with negligible textual differences. The results provide the initial stepping stones for quantifying robustness in neural program analyzers.

Related papers

• NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems [51.8066436083197]
  NeuroBench is a benchmark framework for neuromorphic computing algorithms and systems. NeuroBench is a collaboratively-designed effort from an open community of nearly 100 co-authors across over 50 institutions in industry and academia.
  arXiv  Detail & Related papers  (2023-04-10T15:12:09Z)
• Understanding Neural Code Intelligence Through Program Simplification [3.9704927572880253]
  We propose a model-agnostic approach to identify critical input features for models in code intelligence systems. Our approach, SIVAND, uses simplification techniques that reduce the size of input programs of a CI model. We believe that SIVAND's extracted features may help understand neural CI systems' predictions and learned behavior.
  arXiv  Detail & Related papers  (2021-06-07T05:44:29Z)
• Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference [56.24109486973292]
  We study the interplay between pruning and quantization during the training of neural networks for ultra low latency applications. We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task.
  arXiv  Detail & Related papers  (2021-02-22T19:00:05Z)
• BF++: a language for general-purpose program synthesis [0.483420384410068]
  Most state of the art decision systems based on Reinforcement Learning (RL) are data-driven black-box neural models. We propose a new programming language, BF++, designed specifically for automatic programming of agents in a Partially Observable Markov Decision Process setting.
  arXiv  Detail & Related papers  (2021-01-23T19:44:44Z)
• Neural Software Analysis [18.415191504144577]
  Many software development problems can be addressed by program analysis tools. Recent work has shown tremendous success through an alternative way of creating developer tools, which we call neural software analysis. The key idea is to train a neural machine learning model on numerous code examples, which, once trained, makes predictions about previously unseen code.
  arXiv  Detail & Related papers  (2020-11-16T14:32:09Z)
• Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks [55.98291376393561]
  Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks. Recurrent neural networks (RNNs) are well-suited to long sequential chains of reasoning, but they do not naturally incorporate program structure. We introduce a novel GNN architecture, the Instruction Pointer Attention Graph Neural Networks (IPA-GNN), which improves systematic generalization on the task of learning to execute programs.
  arXiv  Detail & Related papers  (2020-10-23T19:12:30Z)
• Neuro-symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernels [93.58854458951431]
  We present a probabilistic programmed deep kernel learning approach to personalized, predictive modeling of neurodegenerative diseases. Our analysis considers a spectrum of neural and symbolic machine learning approaches. We run evaluations on the problem of Alzheimer's disease prediction, yielding results that surpass deep learning.
  arXiv  Detail & Related papers  (2020-09-16T15:16:03Z)
• On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations [25.96895574298886]
  We evaluate the generalizability of neural program models with respect to semantic-preserving transformations. We use three Java datasets of different sizes and three state-of-the-art neural network models for code. Our results suggest that neural program models based on data and control dependencies in programs generalize better than neural program models based only on abstract syntax trees.
  arXiv  Detail & Related papers  (2020-07-31T20:39:20Z)
• Statistical Guarantees for Regularized Neural Networks [4.254099382808598]
  We develop a general statistical guarantee for estimators that consist of a least-squares term and a regularizer. Our results establish a mathematical basis for regularized estimation of neural networks.
  arXiv  Detail & Related papers  (2020-05-30T15:28:47Z)
• Spiking Neural Networks Hardware Implementations and Challenges: a Survey [53.429871539789445]
  Spiking Neural Networks are cognitive algorithms mimicking neuron and synapse operational principles. We present the state of the art of hardware implementations of spiking neural networks. We discuss the strategies employed to leverage the characteristics of these event-driven algorithms at the hardware level.
  arXiv  Detail & Related papers  (2020-05-04T13:24:00Z)
• Synthetic Datasets for Neural Program Synthesis [66.20924952964117]
  We propose a new methodology for controlling and evaluating the bias of synthetic data distributions over both programs and specifications. We demonstrate, using the Karel DSL and a small Calculator DSL, that training deep networks on these distributions leads to improved cross-distribution generalization performance.
  arXiv  Detail & Related papers  (2019-12-27T21:28:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.