mlsanityData to 7 Oct 2026

Code2Snapshot: Using Code Snapshots for Learning Representations of Source Code

arXiv 2111.01097 ↗First posted 1 Nov 2021cs.SE cs.LG cs.PLcited by 4

Not on the map. Why?

Abstract (arXiv)

There are several approaches for encoding source code in the input vectors of neural models. These approaches attempt to include various syntactic and semantic features of input programs in their encoding. In this paper, we investigate Code2Snapshot, a novel representation of the source code that is based on the snapshots of input programs. We evaluate several variations of this representation and compare its performance with state-of-the-art representations that utilize the rich syntactic and semantic features of input programs. Our preliminary study on the utility of Code2Snapshot in the code summarization and code classification tasks suggests that simple snapshots of input programs have comparable performance to state-of-the-art representations. Interestingly, obscuring input programs have insignificant impacts on the Code2Snapshot performance, suggesting that, for some tasks, neural models may provide high performance by relying merely on the structure of input programs.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 1 Nov 2021.

Builds on

21 of 33 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  4. 2018code2vec: Learning Distributed Representations of Codecited by 249
  5. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 220
  6. 2017Learning to Represent Programs with Graphscited by 219
  7. 2019Machine Learning Testing: Survey, Landscapes and Horizonscited by 213
  8. 2018code2seq: Generating Sequences from Structured Representations of Codecited by 177
  9. 2018The Adverse Effects of Code Duplication in Machine Learning Models of Codecited by 123
  10. 2016A Convolutional Attention Network for Extreme Summarization of Source Codecited by 90
  11. 2020On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformationscited by 41
  12. 2014Learning Natural Coding Conventionscited by 28
9 more
  1. 2021A Survey on Machine Learning Techniques for Source Code Analysiscited by 23
  2. 2021Understanding Neural Code Intelligence Through Program Simplificationcited by 20
  3. 2019A Literature Study of Embeddings on Source Codecited by 18
  4. 2021Memorization and Generalization in Neural Code Intelligence Modelscited by 17
  5. 2020Probing Model Signal-Awareness via Prediction-Preserving Input Minimizationcited by 14
  6. 2020Embedding Java Classes with code2vec: Improvements from Variable Obfuscationcited by 12
  7. 2020Towards Demystifying Dimensions of Source Code Embeddingscited by 9
  8. 2020What You See is What it Means! Semantic Representation Learning of Code based on Visualization and Transfer Learningcited by 3
  9. 2021Code2Image: Intelligent Code Analysis by Computer Vision Techniques and Application to Vulnerability Predictioncited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022Syntax-Guided Program Reduction for Understanding Neural Code Intelligence Modelscited by 7
  2. 2023Study of Distractors in Neural Models of Codecited by 2
  3. 2022Extracting Label-specific Key Input Features for Neural Code Intelligence Modelscited by 0
  4. 2023A Study of Variable-Role-based Feature Enrichment in Neural Models of Codecited by 0