paper-with-me

Papers

Generative Code Modeling with Graphs

2018-05-22 · ICLR 2019 5 · Marc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt, Oleksandr Polozov

Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the generated output. The generative procedure interleaves grammar-driven expansion steps with graph augmentation and neural message passing steps. An experimental evaluation shows that our new model can generate semantically meaningful expressions, outperforming a range of strong baselines.

📄 PDF Abstract BibTeX arXiv:1805.08490

Code (1)

Microsoft/graph-based-code-modelling 공식 구현 tf

Tasks

Structured Prediction

Similar Papers 제목 키워드 기반

Recovering Barabási-Albert Parameters of Graphs through Disentanglement

2021-05-03 · ICLR Workshop GTRL 2021 5 · Cristina Guzman, Daphna Keidar, Tristan Meynier, Andreas Opedal 외

Classical graph modeling approaches such as Erd\H{o}s R\'{e}nyi (ER) random graphs or Barab\'asi-Albert (BA) graphs, here referred to as stylized models, aim to reproduce properties of real-world graphs in an interpretab…

DecoderDisentanglementGraph GenerationGraph Neural Network

Graphite: Iterative Generative Modeling of Graphs

2018-03-28 · Aditya Grover, Aaron Zweig, Stefano Ermon

Graphs are a fundamental abstraction for modeling relational data. However, graphs are discrete and combinatorial in nature, and learning representations suitable for machine learning tasks poses statistical and computat…

Density EstimationGeneral ClassificationLink PredictionNode Classification+1

Deep Generative Model for Periodic Graphs

2022-01-28 · Shiyu Wang, Xiaojie Guo, Liang Zhao

Periodic graphs are graphs consisting of repetitive local structures, such as crystal nets and polygon mesh. Their generative modeling has great potential in real-world applications such as material design and graphics s…

Decodermodel

Learning Graphon Autoencoders for Generative Graph Modeling

2021-05-29 · Hongteng Xu, Peilin Zhao, Junzhou Huang, Dixin Luo

Graphon is a nonparametric model that generates graphs with arbitrary sizes and can be induced from graphs easily. Based on this model, we propose a novel algorithmic framework called \textit{graphon autoencoder} to buil…

Decoder

A Survey on Temporal Graph Representation Learning and Generative Modeling

2022-08-25 · Shubham Gupta, Srikanta Bedathur

Temporal graphs represent the dynamic relationships among entities and occur in many real life application like social networks, e commerce, communication, road networks, biological systems, and many more. They necessita…

Graph Representation LearningRepresentation Learning