ALIGNN
The Atomistic Line Graph Neural Network (https://arxiv.org/abs/2106.01829) introduces a new graph convolution layer that explicitly models both two and three body interactions in atomistic systems (To be published in NPJ Computational Materials Science).
This is achieved by composing two edge-gated graph convolution layers, the first applied to the atomistic line graph L(g) (representing triplet interactions) and the second applied to the atomistic bond graph g (representing pair interactions).
The atomistic graph g consists of a node for each atom i (with atom/node representations hi), and one edge for each atom pair within a cutoff radius (with bond/pair representations eij).
The atomistic line graph L(g) represents relationships between atom triplets: it has nodes corresponding to bonds (sharing representations eij with those in g) and edges corresponding to bond angles (with angle/triplet representations tijk).
The line graph convolution updates the triplet representations and the pair representations; the direct graph convolution further updates the pair representations and the atom representations.
Installation
First create a conda environment: Install miniconda environment from https://conda.io/miniconda.html Based on your system requirements, you'll get a file something like 'Miniconda3-latest-XYZ'.
Now,
bash Miniconda3-latest-Linux-x86_64.sh (for linux)
bash Miniconda3-latest-MacOSX-x86_64.sh (for Mac)
Download 32/64 bit python 3.6 miniconda exe and install (for windows) Now, let's make a conda environment, say "version", choose other name as you like::
conda create --name version python=3.8
source activate version
Now, let's install the package:
git clone https://github.com/usnistgov/alignn.git
cd alignn
python setup.py develop
Examples
Dataset
Users can keep their structure files in POSCAR, .cif, or .xyz files in a directory. In the examples below we will use POSCAR format files. In the same directory, there should be id_prop.csv file.
In this directory, id_prop.csv, the filenames, and correponding target values are kept in comma separated values (csv) format.
Here is an example of training OptB88vdw bandgaps of 50 materials from JARVIS-DFT database. The example is created using the generate_sample_data_reg.py script. Users can modify the script more than 50 data, or make their own dataset in this format. For list of available datasets see Databases.
The dataset in split in 80:10:10 as training-validation-test set (controlled by train_ratio, val_ratio, test_ratio) . To change the split proportion and other parameters, change the config_example.json file. If, users want to train on certain sets and val/test on another dataset, set n_train, n_val, n_test manually in the config_example.json and also set keep_data_order as True there so that random shuffle is disabled.
A brief help guide can be obtained as:
python alignn/scripts/train_folder.py -h
Regression example
Now, the model is trained as follows. Please increase the batch_size parameter to something like 32 or 64 in config_example.json for general trainings.
python alignn/scripts/train_folder.py --root_dir "alignn/examples/sample_data" --config "alignn/examples/sample_data/config_example.json" --output_dir=temp
Classification example
While the above example is for regression, the follwoing example shows a classification task for metal/non-metal based on the above bandgap values. We transform the dataset
into 1 or 0 based on a threshold of 0.01 eV (controlled by the parameter, classification_threshold) and train a similar classification model. Currently, the script allows binary classification tasks only.
python alignn/scripts/train_folder.py --root_dir "alignn/examples/sample_data" --classification_threshold 0.01 --config "alignn/examples/sample_data/config_example.json" --output_dir=temp
Multi-output model example
While the above example regression was for single-output values, we can train multi-output regression models as well. An example is given below for training formation energy per atom, bandgap and total energy per atom simulataneously. The script to generate the example data is provided in the script folder of the sample_data_multi_prop. Another example of training electron and phonon density of states is provided also.
python alignn/scripts/train_folder.py --root_dir "alignn/examples/sample_data_multi_prop" --config "alignn/examples/sample_data/config_example.json" --output_dir=temp
High-throughput model training
Users can try training using multiple example scripts to run multiple dataset (such as JARVIS-DFT, Materials project, QM9_JCTC etc.). Look into the alignn/scripts' folder. This is done primarily to make the trainings more automated rather than making folder/ csv files etc. These scripts automatically download datasets from Databases in [jarvis-tools] (https://github.com/usnistgov/jarvis) package and train several models. Make sure you specify your specific queuing system details in the scripts.
Notes:
- If you are using GPUs, make sure you have a compatible dgl-cuda version installed, for example: dgl-cu101 or dgl-cu111.
- The undirected graph and its line graph is constructured in
jarvis-toolspackage using jarvis.core.graphs
1 maintainer
Release files for alignn 2021.9.29
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| alignn-2021.9.29.tar.gz | 44.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| alignn-2021.9.29-py2.py3-none-any.whl | Python 2, Python 3 | none | any | Details |
Total release size: 111.6 kB
Release files / alignn-2021.9.29.tar.gz
| Download URL | alignn-2021.9.29.tar.gz |
|---|---|
| Size | 44.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d462b629491f52e7b0a3282aa59572ed6eaf67bb9f9d70a3af56f1ce9a9b3fc2
|
|
BLAKE2b-256 checksum How to use checksums |
73230d7c6ce83f3a2367052e01a6e190a5c9be67e3334f42621b3f00afa89029
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.8.8
|
Release files / alignn-2021.9.29-py2.py3-none-any.whl
| Download URL | alignn-2021.9.29-py2.py3-none-any.whl |
|---|---|
| Size | 67.3 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
0a04a416928e299e4d2bf4ff3007e739af510fbbc12b2ecf32bde4f3e2e2aa10
|
|
BLAKE2b-256 checksum How to use checksums |
14a1fdaf229f6c4edd54d29787adf3ecfa4f94b253eabe6b70f42d326bc0db53
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.8.8
|
