Learning to Represent Programs with Graphs | TDLS

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=Q66iNWiHt_U


Duration: 1:15:49
1,090 views
15

Toronto Deep Learning Series, 25 June 2018

For slides and more information, visit https://tdls.a-i.science/events/2018-06-25/

Paper Review: https://arxiv.org/abs/1711.00740

Speaker: https://www.linkedin.com/in/amirfz/
Organizer: https://www.linkedin.com/in/amirfz/

Host: http://www.rbc.com/futuremakers/

Paper abstract:
"Learning tasks on source code (i.e., formal languages) have been considered recently, but most work has tried to transfer natural language methods and does not capitalize on the unique opportunities offered by code's known syntax. For example, long-range dependencies induced by using the same variable or function in distant locations are often not considered. We propose to use graphs to represent both the syntactic and semantic structure of code and use graph-based deep learning methods to learn to reason over program structures.
In this work, we present how to construct graphs from source code and how to scale Gated Graph Neural Networks training to such large graphs. We evaluate our method on two tasks: VarNaming, in which a network attempts to predict the name of a variable given its usage, and VarMisuse, in which the network learns to reason about selecting the correct variable that should be used at a given program location. Our comparison to methods that use less structured program representations shows the advantages of modeling known structure, and suggests that our models learn to infer meaningful names and to solve the VarMisuse task in many cases. Additionally, our testing showed that VarMisuse identifies a number of bugs in mature open-source projects."



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2018-09-05Recurrent Models of Visual Attention | TDLS
2018-08-28Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates | TDLS
2018-08-20TDLS: Large-Scale Unsupervised Deep Representation Learning for Brain Structure
2018-08-14Principles of Riemannian Geometry in Neural Networks | TDLS
2018-08-07Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond | TDLS
2018-07-30Program Language Translation Using a Grammar-Driven Tree-to-Tree Model | TDLS
2018-07-23Explainable Neural Networks based on Additive Index Models | TDLS
2018-07-18TMLS2018 - Machine Learning in Production, Panel Discussion
2018-07-16Flexible Neural Representation for Physics Prediction | AISC Trending Paper
2018-07-10Connectionist Temporal Classification, Labelling Unsegmented Sequence Data with RNN | TDLS
2018-06-25Learning to Represent Programs with Graphs | TDLS
2018-06-19Quantum generative adversarial networks | TDLS Author Speaking
2018-06-12[SAGAN] Self-Attention Generative Adversarial Networks | TDLS
2018-06-05[ELMo] Deep Contextualized Word Representations | AISC
2018-05-23Few-Shot Learning Through an Information Retrieval Lens | TDLS
2018-05-14Improving Supervised Bilingual Mapping of Word Embeddings | TDLS
2018-05-01[Word2Bits] Quantized Word Vectors | AISC
2017-11-15TMLS2017: Transitioning to Data Science, Panel Discussion


Tags:
deep learning
graph neural net
machine learning on source code
graph neural network
neural code parsing
learning representation
graph convolutional networks