Deep Learning for Big Code

Overview

The objective of the seminar is to:

Introduce students to the emerging field of Deep Learning for Big Code.
Learn how machine learning models can be used to solve practical challenges in software engineering and programming beyond traditional methods.
Highlight the latest research and work opportunities in industry and academia available on this topic.

The seminar is carried out as a set of presentations (2 each lecture) chosen from a set of available papers (available below). The grade is determined as a function of the presentation, handling questions and answers, and participation:

Schedule

Date	Title	Presenter	Advisor
22.02	Introduction to the seminar (topics, objectives, structure):	Veselin Raychev
	Candidate papers to choose from
08.03	LambdaNet: Probabilistic Type Inference using Graph Neural Networks	Ahmed Bouhoula	Matthew
15.03	Deep Learning based Vulnerability Detection: Are We There Yet?	Julien Tinguely	Max
	Synthesizing Programs for Images using Reinforced Adversarial Learning	Julia Bazinska	Mark
22.03	Estimating Types in Binaries using Predictive Modeling	Laurin Brandner	Veselin
	Unsupervised Translation of Programming Languages	Fredin Thazhathukunnel	Marc
29.03	Neural Software Analysis	Lam Nguyen Thiet	Luca
12.04	Learning semantic program embeddings with graph interval neural network	Remo Geissbühler	Max
	Programmatically Interpretable Reinforcement Learning	Gabriela Krasnopolska	Mark
26.04	PHOG: Probabilistic Model for Code	Mike Boss	Marc
	Locate-Then-Detect: Real-time Web Attack Detection via Attention-based Deep Neural Networks	Jason Friedman	Johannes
03.05	Neural Guided Constraint Logic Programming for Program Synthesis	Jannis Bolik	Matthew
	CodeBERT: A Pre-Trained Model for Programming and Natural Languages	Sven Wiesner	Johannes