PyTorch implementation for "HyperSPNs: Compact and Expressive Probabilistic Circuits", NeurIPS 2021

Last update: Nov 08, 2022

Overview

HyperSPN

This repository contains code for the paper:

HyperSPNs: Compact and Expressive Probabilistic Circuits

"HyperSPNs: Compact and Expressive Probabilistic Circuits"
Andy Shih, Dorsa Sadigh, Stefano Ermon
In Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021

@inproceedings{ShihSEneurips21,
  author    = {Andy Shih and Dorsa Sadigh and Stefano Ermon},
  title     = {HyperSPNs: Compact and Expressive Probabilistic Circuits},
  booktitle = {Advances in Neural Information Processing Systems 34 (NeurIPS)},
  month     = {december},
  year      = {2021},
  keywords  = {conference}
}

Installation

conda env create -f environment.yml

Optionally, for EinsumNetworks:

cd EinsumNetworks
pip3 install -r requirements.txt

Datasets and Repos

The Twenty Datasets benchmark is from here.

The Amazon Baby Registries benchmark is from here. The dataset was converted from the set format into the binary format.

The Einsum Network repository is from here.

Commands

Experiments can be launched with the helper bash files

runid=0
bash bashfiles/run_hyperspn.bash ${runid} 5
bash bashfiles/run_hyperspn.bash ${runid} 10
bash bashfiles/run_hyperspn.bash ${runid} 20

bash bashfiles/run_spn.bash ${runid} 1e-3
bash bashfiles/run_spn.bash ${runid} 1e-4
bash bashfiles/run_spn.bash ${runid} 1e-5

cd EinsumNetworks/src/
python train_svhn_mixture.py --run=0
python train_svhn_mixture.py --nn --run=0

PyTorch implementation for "HyperSPNs: Compact and Expressive Probabilistic Circuits", NeurIPS 2021

Related tags

Overview

HyperSPN

Installation

Datasets and Repos

Commands

Owner

The fastai deep learning library

Data cleaning, missing value handle, EDA use in this project

DirectVoxGO reconstructs a scene representation from a set of calibrated images capturing the scene.

Compute descriptors for 3D point cloud registration using a multi scale sparse voxel architecture

Code for Paper Predicting Osteoarthritis Progression via Unsupervised Adversarial Representation Learning

FLAVR is a fast, flow-free frame interpolation method capable of single shot multi-frame prediction

Weakly Supervised Scene Text Detection using Deep Reinforcement Learning

Pytorch implementation of Learning with Opponent-Learning Awareness

Resources for our AAAI 2022 paper: "LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification".

[3DV 2021] A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks

PyTorch implementation of the paper:A Convolutional Approach to Melody Line Identification in Symbolic Scores.

Contains source code for the winning solution of the xView3 challenge

Neighborhood Contrastive Learning for Novel Class Discovery

Large scale PTM - PPI relation extraction

Attendance Monitoring with Face Recognition using Python

ReSSL: Relational Self-Supervised Learning with Weak Augmentation

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

Emotion Recognition from Facial Images

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Framework for Spectral Clustering on the Sparse Coefficients of Learned Dictionaries