Molecular dynamics (MD) simulation is a widely used technique to simulat...
Learning program semantics from raw source code is challenging due to th...
Learning from structured data is a core machine learning task. Commonly,...
Traditional generative models are limited to predicting sequences of ter...
Machine learning-based program analyses have recently shown the promise ...
Recent advancements in deep learning-based modeling of molecules promise...
Neural sequence-to-sequence models are finding increasing use in editing...
To continuously improve quality and reflect changes in data, machine
lea...
We present a technique to infer lower bounds on the worst-case runtime
c...
While a wide range of interpretable generative procedures for graphs exi...
Semantic code search is the task of retrieving relevant code given a nat...
This paper presents a new Graph Neural Network (GNN) type using feature-...
Program synthesis of general-purpose source code from natural language
s...
Summarization of long sequences into a concise statement is a core probl...
We introduce the problem of learning distributed representations of edit...
We consider the problem of neural semantic parsing, which translates nat...
We present a neural semantic parser that translatesnatural language ques...
Graphs are ubiquitous data structures for representing interactions betw...
Generative models for source code are an interesting structured predicti...
We present graph partition neural networks (GPNN), an extension of graph...
Learning tasks on source code (i.e., formal languages) have been conside...
We study machine learning formulations of inductive program synthesis; t...
We study machine learning formulations of inductive program synthesis; g...
Graph-structured data appears frequently in domains including chemistry,...