Presenter:

Miltos Allamanis, Microsoft Research, Cambridge [HOME] [PUBS] [SLIDES]

Readings:

Primary: Allamanis et al. [1] [PDF] Secondary: Brockschmidt et al. [3] [PDF], Li et al. [6] [PDF],

References:

[1]   Allamanis, Miltiadis, Marc Brockschmidt, and Mahmoud Khademi. Learning to represent programs with graphs. ICLR, 2018.

[2]   Miltadis et al. A survey of machine learning for big code and naturalness. ACM Computing Surveys, 2018.

[3]   Marc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt, Oleksandr Polozov. Generative code modeling with graphs. ICLR, 2019.

[4]   Cvitkovic, Milan, Badal Singh, and Anima Anandkumar. Open Vocabulary Learning on Source Code with a Graph-Structured Cache. CoRR, arXiv:1810.08305 2018.

[5]   Fernandes, Patrick, Miltiadis Allamanis, and Marc Brockschmidt. Structured Neural Summarization. ICLR, 2019.

[6]   Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel. Gated graph sequence neural networks. ICLR, 2016.