Inferring Javascript types using Graph Neural Networks.
作者： Jessica Schrouff , Kai Wohlfahrt , Liam Atkinson , Bruno Marnette
DOI:
关键词: Code (cryptography) 、 Computer science 、 Artificial intelligence 、 JavaScript 、 Deep learning 、 Graph neural networks 、 Security token 、 Source code 、 Programming language
摘要: … As a first step towards automatic code repair, we implemented a graph neural network model that predicts token types for Javascript programs. The predictions achieve an accuracy …
harvard.edu
arxiv.org参考文章(15)
Zoubin Ghahramani, Yarin Gal, Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning arXiv: Machine Learning. ,(2015)
F. Scarselli, M. Gori, Ah Chung Tsoi, M. Hagenbuchner, G. Monfardini, The Graph Neural Network Model IEEE Transactions on Neural Networks. ,vol. 20, pp. 61- 80 ,(2009) , 10.1109/TNN.2008.2005605
Veselin Raychev, Martin Vechev, Andreas Krause, Predicting Program Properties from "Big Code" symposium on principles of programming languages. ,vol. 50, pp. 111- 124 ,(2015) , 10.1145/2676726.2677009
Max Welling, Thomas N. Kipf, Semi-Supervised Classification with Graph Convolutional Networks arXiv: Learning. ,(2016)
Zhaogui Xu, Xiangyu Zhang, Lin Chen, Kexin Pei, Baowen Xu, Python probabilistic type inference with natural language support foundations of software engineering. pp. 607- 618 ,(2016) , 10.1145/2950290.2950343
Patrick F. Riley, Justin Gilmer, George E. Dahl, Oriol Vinyals, Samuel S. Schoenholz, Neural Message Passing for Quantum Chemistry international conference on machine learning. pp. 1263- 1272 ,(2017)
M. Welling, T.N. Kipf, R. van den Berg, Graph Convolutional Matrix Completion arXiv: Machine Learning. ,(2017)
Benjamin Recht, Ameet Talwalkar, Ekaterina Gonina, Kevin G. Jamieson, Moritz Hardt, Afshin Rostamizadeh, Liam Li, Massively Parallel Hyperparameter Tuning ,(2018)
Leslie N. Smith, A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay arXiv: Learning. ,(2018)
Richard Liaw, Robert Nishihara, Philipp Moritz, Ion Stoica, Eric Liang, Joseph E. Gonzalez, Tune: A Research Platform for Distributed Model Selection and Training. arXiv: Learning. ,(2018)