Authors implementation of LieTransformer: Equivariant Self-Attention for Lie Groups

Overview

LieTransformer

This repository contains the implementation of the LieTransformer used for experiments in the paper LieTransformer: Equivariant self-attention for Lie Groups

Pattern recognition Molecular property prediction Particle Dynamics
Constellations Rotating molecule Particle trajectories

Introduction

LieTransformer is a equivariant Transformer-like model, built out of equivariant self attention layers (LieSelfAttention). The model can be made equivariant to any Lie group, simply by providing and implementation of the group of interest. A number of commonly used groups are already implemented, building off the work of LieConv. Switching group equivariance requires no change to model architecture, only passsing a different group to the model.

Architecture

The overall architecture of the LieTransformer is similar to the architecture of the original Transformer, interleaving series of attention layers and pointwise MLPs in residual blocks. The architecture of the LieSelfAttention blocks differs however, and can be seen below. For more details, please see the paper.

model diagram

Installation

To repoduce the experiments in this library, first clone the repo via https://github.com/anonymous-code-0/lie-transformer. To install the dependencies and create a virtual environment, execute setup_virtualenv.sh. Alternatively you can install the library and its dependencies without creating a virtual environment via pip install -e ..

To install the library as a dependency for another project use https://github.com/anonymous-code-0/lie-transformer.

Alternatively, you can install all the dependencies using pip install -r requirements.txt. If you do so, you will need to install the LieConv, Forge, and this repo itself (using the pip install -e command). Please note the version of LieConv used in this project is a slightly modified version of the original repo which fixes a bug for updated PyTorch versions.

Training a model

Example command to train a model (in this case the Set Transformer on the constellation dataset):

python3 scripts/train_constellation.py --data_config configs/constellation.py --model_config configs/set_transformer.py --run_name my_experiment --learning_rate=1e-4 --batch_size 128

The model and the dataset can be chosen by specifying different config files. Flags for configuring the model and the dataset are available in the respective config files. The project is using forge for configs and experiment management. Please refer to examples for details.

Counting patterns in the constellation dataset

The first task implemented is counting patterns in the constellation dataset. We generate a fixed dataset of constellations, where each constellation consists of 0-8 patterns; each pattern consists of corners of a shape. Currently available shapes are triangle, square, pentagon and an L. The task is to count the number of occurences of each pattern. To save to file the constellation datasets, run before training:

python3 scripts/data_to_file.py

Else, the constellation datasets are regenerated at the beginning of the training.

Dataset and model consistency

When changing the dataset parameters (e.g. number of patterns, types of patterns etc) make sure that the model parameters are adjusted accordingly. For example patterns=square,square,triangle,triangle,pentagon,pentagon,L,L means that there can be four different patterns, each repeated two times. That means that counting will involve four three-way classification tasks, and so that n_outputs and output_dim in classifier.py needs to be set to 4 and 3, respectively. All this can be set through command-line arguments.

Results

Constellations results

QM9

This dataset consists of 133,885 small inorganic molecules described by the location and charge of each atom in the molecule, along with the bonding structure of the molecule. The dataset includes 19 properties of each molecule, such as various rotational constants, energies and enthalpies. We aim to predict 12 of these properties.

python scripts/train_molecule.py \
    --run_name "molecule_homo" \
    --model_config "configs/molecule/eqv_transformer_model.py" \
    --model_seed 0
    --data_seed 0 \
    --task homo

Configurable scripts for running the experiments in the paper exist in the scripts folder, scripts/train_molecule_SE3transformer.sh, scripts/train_molecule_SE3lieconv.sh.

Results

QM9 results

Hamiltonian dynamics

In this experiment we aim to predict the trajectory of a number of particles connected together by a series of springs. This is done by learning the Hamiltonian of the system from observed trajectories.

The following command generates a dataset of trajectories and trains LieTransformer on it

T(2) default: python scripts/train_dynamics.py
SE(2) default: python scripts/train_dynamics.py --group 'SE(2)_canonical' --lift_samples 2 --num_layers 3 --dim_hidden 80

Results

Rollout MSE Example Trajectories
dynamics rollout trajectories

Contributing

Contributions are best developed in separate branches. Once a change is ready, please submit a pull request with a description of the change. New model and data configs should go into the config folder, and the rest of the code should go into the eqv_transformer folder.

Implementation of Fast Transformer in Pytorch

Fast Transformer - Pytorch Implementation of Fast Transformer in Pytorch. This only work as an encoder. Yannic video AI Epiphany Install $ pip install

Phil Wang 167 Dec 27, 2022
Exploration-Exploitation Dilemma Solving Methods

Exploration-Exploitation Dilemma Solving Methods Medium article for this repo - HERE In ths repo I implemented two techniques for tackling mentioned t

Aman Mishra 6 Jan 25, 2022
Pytorch implementation of NeurIPS 2021 paper: Geometry Processing with Neural Fields.

Geometry Processing with Neural Fields Pytorch implementation for the NeurIPS 2021 paper: Geometry Processing with Neural Fields Guandao Yang, Serge B

Guandao Yang 162 Dec 16, 2022
Import Python modules from dicts and JSON formatted documents.

Paker Paker is module for importing Python packages/modules from dictionaries and JSON formatted documents. It was inspired by httpimporter. Important

Wojciech Wentland 1 Sep 07, 2022
Rank 3 : Source code for OPPO 6G Data Generation Challenge

OPPO 6G Data Generation with an E2E Framework Homepage of OPPO 6G Data Generation Challenge Datasets H1_32T4R.mat H2_32T4R.mat Please put the original

Sen Pei 97 Jan 07, 2023
State-of-the-art language models can match human performance on many tasks

Status: Archive (code is provided as-is, no updates expected) Grade School Math [Blog Post] [Paper] State-of-the-art language models can match human p

OpenAI 259 Jan 08, 2023
Code, final versions, and information on the Sparkfun Graphical Datasheets

Graphical Datasheets Code, final versions, and information on the SparkFun Graphical Datasheets. Generated Cells After Running Script Example Complete

SparkFun Electronics 102 Jan 05, 2023
Unofficial PyTorch implementation of SimCLR by Google Brain

Unofficial PyTorch implementation of SimCLR by Google Brain

Rishabh Anand 2 Oct 13, 2021
Easily Process a Batch of Cox Models

ezcox: Easily Process a Batch of Cox Models The goal of ezcox is to operate a batch of univariate or multivariate Cox models and return tidy result. ⏬

Shixiang Wang 15 May 23, 2022
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark (ICCV 2021)

Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark (ICCV 2021) Kun Wang, Zhenyu Zhang, Zhiqiang Yan, X

kunwang 66 Nov 24, 2022
COD-Rank-Localize-and-Segment (CVPR2021)

COD-Rank-Localize-and-Segment (CVPR2021) Simultaneously Localize, Segment and Rank the Camouflaged Objects Full camouflage fixation training dataset i

JingZhang 52 Dec 20, 2022
Codebase for the solution that won first place and was awarded the most human-like agent in the 2021 NeurIPS Competition MineRL BASALT Challenge.

KAIROS MineRL BASALT Codebase for the solution that won first place and was awarded the most human-like agent in the 2021 NeurIPS Competition MineRL B

Vinicius G. Goecks 37 Oct 30, 2022
[ICLR2021] Unlearnable Examples: Making Personal Data Unexploitable

Unlearnable Examples Code for ICLR2021 Spotlight Paper "Unlearnable Examples: Making Personal Data Unexploitable " by Hanxun Huang, Xingjun Ma, Sarah

Hanxun Huang 98 Dec 07, 2022
Real-time 3D multi-person detection made easy with OpenPose and the ZED

OpenPose ZED This sample show how to simply use the ZED with OpenPose, the deep learning framework that detects the skeleton from a single 2D image. T

blanktec 5 Nov 06, 2020
phylotorch-bito is a package providing an interface to BITO for phylotorch

phylotorch-bito phylotorch-bito is a package providing an interface to BITO for phylotorch Dependencies phylotorch BITO Installation Get the source co

Mathieu Fourment 2 Sep 01, 2022
Deep learning model for EEG artifact removal

DeepSeparator Introduction Electroencephalogram (EEG) recordings are often contaminated with artifacts. Various methods have been developed to elimina

23 Dec 21, 2022
Hashformers is a framework for hashtag segmentation with transformers.

Hashtag segmentation is the task of automatically inserting the missing spaces between the words in a hashtag. Hashformers applies Transformer models

Ruan Chaves 41 Nov 09, 2022
Two-stage CenterNet

Probabilistic two-stage detection Two-stage object detectors that use class-agnostic one-stage detectors as the proposal network. Probabilistic two-st

Xingyi Zhou 1.1k Jan 03, 2023
Count GitHub Stars ⭐

Count GitHub Stars per Day ⭐ Track GitHub stars per day over a date range to measure the open-source popularity of different repositories. Requirement

Ultralytics 20 Nov 20, 2022
Parameterising Simulated Annealing for the Travelling Salesman Problem

Parameterising Simulated Annealing for the Travelling Salesman Problem

Gary Sun 55 Jun 15, 2022