Latent Execution for Neural Program Synthesis

Overview

Latent Execution for Neural Program Synthesis

This repo provides the code to replicate the experiments in the paper

Xinyun Chen, Dawn Song, Yuandong Tian, Latent Execution for Neural Program Synthesis, in NeurIPS 2021.

Paper [arXiv] [NeurIPS]

Prerequisites

PyTorch

Dataset

Sample Usage

  1. To run our full latent program synthesizer (LaSynth):

python run.py --latent_execution --operation_predictor --decoder_self_attention

  1. To run our program synthesizer without partial program execution (NoPartialExecutor):

python run.py --latent_execution --operation_predictor --decoder_self_attention --no_partial_execution

  1. To run the RobustFill model:

python run.py

  1. To run the Property Signatures model:

python run.py --use_properties

Run experiments

In the following we list some important arguments for experiments:

  • --data_folder: path to the dataset.
  • --model_dir: path to the directory that stores the models.
  • --load_model: path to the pretrained model (optional).
  • --eval: adding this command will enable the evaluation mode; otherwise, the model will be trained by default.
  • --num_epochs: number of training epochs. The default value is 10, but usually 1 epoch is enough for a decent performance.
  • --log_interval LOG_INTERVAL: saving checkpoints every LOG_INTERVAL steps.
  • --latent_execution: Enable the model to learn the latent executor module.
  • --no_partial_execution: Enable the model to learn the latent executor module, but this module is not used by the program synthesizer, and only adds to the training loss.
  • --operation_predictor: Enable the model to learn the operation predictor module.
  • --use_properties: Run the Property Signatures baseline.
  • --iterative_retraining_prog_gen: Decode training programs for iterative retraining.

More details can be found in arguments.py.

Citation

If you use the code in this repo, please cite the following paper:

@inproceedings{chen2021latent,
  title={Latent Execution for Neural Program Synthesis},
  author={Chen, Xinyun and Song, Dawn and Tian, Yuandong},
  booktitle={Advances in Neural Information Processing Systems},
  year={2021}
}

License

This repo is CC-BY-NC licensed, as found in the LICENSE file.

References

[1] Devlin et al., RobustFill: Neural Program Learning under Noisy I/O, ICML 2017.

[2] Odena and Sutton, Learning to Represent Programs with Property Signatures, ICLR 2020.

[3] Chen et al., Execution-Guided Neural Program Synthesis, ICLR 2019.

Owner
Xinyun Chen
Ph.D. student, UC Berkeley.
Xinyun Chen
A collection of Reinforcement Learning algorithms from Sutton and Barto's book and other research papers implemented in Python.

Reinforcement-Learning-Notebooks A collection of Reinforcement Learning algorithms from Sutton and Barto's book and other research papers implemented

Pulkit Khandelwal 1k Dec 28, 2022
Beancount-mercury - Beancount importer for Mercury Startup Checking

beancount-mercury beancount-mercury provides an Importer for converting CSV expo

Michael Lynch 4 Oct 31, 2022
PyTorch implementation of paper A Fast Knowledge Distillation Framework for Visual Recognition.

FKD: A Fast Knowledge Distillation Framework for Visual Recognition Official PyTorch implementation of paper A Fast Knowledge Distillation Framework f

Zhiqiang Shen 129 Dec 24, 2022
Deeper DCGAN with AE stabilization

AEGeAN Deeper DCGAN with AE stabilization Parallel training of generative adversarial network as an autoencoder with dedicated losses for each stage.

Tyler Kvochick 36 Feb 17, 2022
FS-Mol: A Few-Shot Learning Dataset of Molecules

FS-Mol is A Few-Shot Learning Dataset of Molecules, containing molecular compounds with measurements of activity against a variety of protein targets. The dataset is presented with a model evaluation

Microsoft 114 Dec 15, 2022
VOS: Learning What You Don’t Know by Virtual Outlier Synthesis

VOS This is the source code accompanying the paper VOS: Learning What You Don’t

248 Dec 25, 2022
Emotion classification of online comments based on RNN

emotion_classification Emotion classification of online comments based on RNN, the accuracy of the model in the test set reaches 99% data: Large Movie

1 Nov 23, 2021
Code for "On the Effects of Batch and Weight Normalization in Generative Adversarial Networks"

Note: this repo has been discontinued, please check code for newer version of the paper here Weight Normalized GAN Code for the paper "On the Effects

Sitao Xiang 182 Sep 06, 2021
[EMNLP 2021] Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training

RoSTER The source code used for Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training, p

Yu Meng 60 Dec 30, 2022
DeiT: Data-efficient Image Transformers

DeiT: Data-efficient Image Transformers This repository contains PyTorch evaluation code, training code and pretrained models for DeiT (Data-Efficient

Facebook Research 3.2k Jan 06, 2023
Unified tracking framework with a single appearance model

Paper: Do different tracking tasks require different appearance model? [ArXiv] (comming soon) [Project Page] (comming soon) UniTrack is a simple and U

ZhongdaoWang 300 Dec 24, 2022
Codebase to experiment with a hybrid Transformer that combines conditional sequence generation with regression

Regression Transformer Codebase to experiment with a hybrid Transformer that combines conditional sequence generation with regression . Development se

International Business Machines 27 Jan 05, 2023
A simple, high level, easy-to-use open source Computer Vision library for Python.

ZoomVision : Slicing Aid Detection A simple, high level, easy-to-use open source Computer Vision library for Python. Installation Installing dependenc

Nurettin Sinanoğlu 2 Mar 04, 2022
Code of paper: "DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks"

DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks Abstract: Adversarial training has been proven to

倪仕文 (Shiwen Ni) 58 Nov 10, 2022
Deep learned, hardware-accelerated 3D object pose estimation

Isaac ROS Pose Estimation Overview This repository provides NVIDIA GPU-accelerated packages for 3D object pose estimation. Using a deep learned pose e

NVIDIA Isaac ROS 41 Dec 18, 2022
🥇Samsung AI Challenge 2021 1등 솔루션입니다🥇

MoT - Molecular Transformer Large-scale Pretraining for Molecular Property Prediction Samsung AI Challenge for Scientific Discovery This repository is

Jungwoo Park 44 Dec 03, 2022
Check out the StyleGAN repo and place it in the same directory hierarchy as the present repo

Variational Model Inversion Attacks Kuan-Chieh Wang, Yan Fu, Ke Li, Ashish Khisti, Richard Zemel, Alireza Makhzani Most commands are in run_scripts. W

Jackson Wang 15 Dec 26, 2022
Code for generating the figures in the paper "Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?"

Code for running simulations for the paper "Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Lin

Matthew Farrell 1 Nov 22, 2022
A simple baseline for the 2022 IEEE GRSS Data Fusion Contest (DFC2022)

DFC2022 Baseline A simple baseline for the 2022 IEEE GRSS Data Fusion Contest (DFC2022) This repository uses TorchGeo, PyTorch Lightning, and Segmenta

isaac 24 Nov 28, 2022
Satellite labelling tool for manual labelling of storm top features such as overshooting tops, above-anvil plumes, cold U/Vs, rings etc.

Satellite labelling tool About this app A tool for manual labelling of storm top features such as overshooting tops, above-anvil plumes, cold U/Vs, ri

Czech Hydrometeorological Institute - Satellite Department 10 Sep 14, 2022