mlsanityData to 14 Oct 2026

HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations

arXiv 2205.15479 ↗First posted 31 May 2022cs.SE cs.AI cs.PLcited by 9

Not on the map. Why?

Abstract (arXiv)

We propose a novel method for code summarization utilizing Heterogeneous Code Representations (HCRs) and our specially designed HierarchyNet. HCRs effectively capture essential code features at lexical, syntactic, and semantic levels by abstracting coarse-grained code elements and incorporating fine-grained program elements in a hierarchical structure. Our HierarchyNet method processes each layer of the HCR separately through a unique combination of the Heterogeneous Graph Transformer, a Tree-based CNN, and a Transformer Encoder. This approach preserves dependencies between code elements and captures relations through a novel Hierarchical-Aware Cross Attention layer. Our method surpasses current state-of-the-art techniques, such as PA-Former, CAST, and NeuralCodeSum.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 34 of its 64 references that are in the map. First posted on arXiv 31 May 2022.

Builds on

34 of 64 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  5. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  7. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
  8. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  9. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  10. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 609
  11. 2020Heterogeneous Graph Transformercited by 582
  12. 2021Unified Pre-training for Program Understanding and Generationcited by 366
22 more
  1. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 306
  2. 2020Unsupervised Translation of Programming Languagescited by 263
  3. 2018code2vec: Learning Distributed Representations of Codecited by 250
  4. 2017Learning to Represent Programs with Graphscited by 220
  5. 2018code2seq: Generating Sequences from Structured Representations of Codecited by 179
  6. 2020A Transformer-based Approach for Source Code Summarizationcited by 133
  7. 2018Improving Automatic Source Code Summarization via Deep Reinforcement Learningcited by 100
  8. 2020Improved Code Summarization via a Graph Neural Networkcited by 79
  9. 2019A Neural Model for Generating Natural Language Summaries of Program Subroutinescited by 77
  10. 2019Code Generation as a Dual Task of Code Summarizationcited by 62
  11. 2018Structured Neural Summarizationcited by 54
  12. 2020Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformationscited by 49
  13. 2020On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformationscited by 44
  14. 2021Multilingual training for Software Engineeringcited by 43
  15. 2020Adversarial Robustness for Codecited by 38
  16. 2022SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representationscited by 36
  17. 2021CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Treescited by 32
  18. 2020Code Summarization with Structure-induced Transformercited by 29
  19. 2021How could Neural Networks understand Programs?cited by 26
  20. 2018Input Combination Strategies for Multi-Source Transformer Decodercited by 22
  21. 2020TreeCaps: Tree-Based Capsule Networks for Source Code Processingcited by 16
  22. 2019Detecting Deep Neural Network Defects with Data Flow Analysiscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 3; 2026: 1.

9 papers.

  1. 2025SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugscited by 22
  2. 2023CodeTF: One-stop Transformer Library for State-of-the-art Code LLMscited by 21
  3. 2024CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMscited by 18
  4. 2023Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learningcited by 12
  5. 2026ShieldedCode: Learning Robust Representations for Virtual Machine Protected Codecited by 8
  6. 2024XMainframe: A Large Language Model for Mainframe Modernizationcited by 6
  7. 2024WAFFLE: Finetuning Multi-Modal Models for Automated Front-End Developmentcited by 5
  8. 2025Bridging Code Graphs and Large Language Models for Better Code Understandingcited by 2
  9. 2025Simple and Effective Baselines for Code Summarisation Evaluationcited by 0