mlsanityData to 7 Oct 2026

Compositionality-Aware Graph2Seq Learning

arXiv 2201.12178 ↗First posted 28 Jan 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graphs are a highly expressive data structure, but it is often difficult for humans to find patterns from a complex graph. Hence, generating human-interpretable sequences from graphs have gained interest, called graph2seq learning. It is expected that the compositionality in a graph can be associated to the compositionality in the output sequence in many graph2seq tasks. Therefore, applying compositionality-aware GNN architecture would improve the model performance. In this study, we adopt the multi-level attention pooling (MLAP) architecture, that can aggregate graph representations from multiple levels of information localities. As a real-world example, we take up the extreme source code summarization task, where a model estimate the name of a program function from its source code. We demonstrate that the model having the MLAP architecture outperform the previous state-of-the-art model with more than seven times fewer parameters than it.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 30 references that are in the map. First posted on arXiv 28 Jan 2022.

Builds on

25 of 30 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  10. 2015Gated Graph Sequence Neural Networkscited by 792
  11. 2018code2vec: Learning Distributed Representations of Codecited by 249
  12. 2017Learning to Represent Programs with Graphscited by 219
13 more
  1. 2018code2seq: Generating Sequences from Structured Representations of Codecited by 177
  2. 2020GraphNorm: A Principled Approach to Accelerating Graph Neural Network Trainingcited by 116
  3. 2014Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognitioncited by 111
  4. 2016A Convolutional Attention Network for Extreme Summarization of Source Codecited by 90
  5. 2019Graph Transformer for Graph-to-Sequence Learningcited by 82
  6. 2018Structured Neural Summarizationcited by 53
  7. 2018Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networkscited by 36
  8. 2019Modeling Graph Structure in Transformer for Better AMR-to-Text Generationcited by 35
  9. 2018Deep Graph Convolutional Encoders for Structured Data to Text Generationcited by 27
  10. 2020Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networkscited by 25
  11. 2016Knowledge Questions from Knowledge Graphscited by 15
  12. 2021Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localitiescited by 8
  13. 2018Bidirectional Attentional Encoder-Decoder Model and Bidirectional Beam Search for Abstractive Summarizationcited by 4

Built on by

Not cited yet.