linqs/dickens-icml24

Experiments for "Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning".

Requirements

These experiments expect that you are running on a POSIX (Linux/Mac) system. The specific application dependencies are as follows:

• Bash >= 4.0
• Java >= 7
• Python >= 3.7

Setup

These scripts assume you have already built and installed NeuPSL from our repository. If you have not, please follow the instructions in our NeuPSL repository.

Data

Data for the HL-MRF experiments in the top-level scripts directory will be pulled from the psl-examples repository Data for the deep HL-MRF experiments must be created by running the create_data.py scripts in the citation and mnist-addition directories.

Models

Models for the HL-MRF experiments in the top-level scripts directory will be pulled from the psl-examples repository Models for the deep HL-MRF experiments are in the citation and mnist-addition directories. An additional step is required to create the deep HL-MRF models for the citation experiments as the neural component is pretrained. After creating the data, run citation/scripts/setup-networks.py. This will pre-train the neural component for the NeuPSL models.

Running Experiments

The experiments are organized into a series of scripts. Each script is responsible for running a single experiment. To run all experiments, simply run the run.sh script in the top level directory. To run a single experiment, run its corresponding python script.

The HL-MRF timing experiments are found in the top level scripts directory. scripts/run_dual_bcd_inference_regularization_experiments.py runs the dual BCD regularization experiments. scripts/run_weight_learning_inference_timing_experiments.py runs the weight learning runtime experiments. scripts/run_weight_learning_performance_experiments.py runs the HL-MRF weight learning runtime experiments.

The deep HL-MRF experiments are in the citation/scripts and mnist-addition/scripts directories.

Results

For the HL-MRF experiments, results will be written to the top-level results directory. For the Deep HL-MRF experiments, results will be written to the results directory in the citation and mnist-addition directories. To parse the results for the HL-MRF experiments, run the parse_results.py script in the top-level scripts directory. To parse the results for the Deep HL-MRF experiments, run the parse_results.py script in the citation/scripts and mnist-addition/scripts directories.

dickens-icml24's Issues

./run.sh citation

Hello, I've done mvn install -P gurobi, but when I run citation I get an error and I don't know how to fix it, the version of pslpython is the version that follows neupsl.
now, I'm having the following problem in error.txt
I'm not sure if it's because of an issue with tf's version, as I can work fine in neupsl, can you help me solve this problem.
out.txt
outerr.txt

[INFO] ------------------------------------------------------------------------
[INFO] Reactor Summary for psl 3.0.1-SNAPSHOT:
[INFO]
[INFO] psl ................................................ SUCCESS [ 0.798 s]
[INFO] psl-core ........................................... SUCCESS [02:41 min]
[INFO] psl-parser ......................................... SUCCESS [ 4.717 s]
[INFO] psl-java ........................................... SUCCESS [ 4.190 s]
[INFO] psl-cli ............................................ SUCCESS [ 7.946 s]
[INFO] psl-runtime ........................................ SUCCESS [ 5.277 s]
[INFO] psl-python ......................................... SUCCESS [ 7.497 s]
[INFO] ------------------------------------------------------------------------
[INFO] BUILD SUCCESS
[INFO] ------------------------------------------------------------------------
[INFO] Total time: 03:12 min
[INFO] Finished at: 2024-09-20T13:47:17+08:00
[INFO] ------------------------------------------------------------------------
pip list
Package Version

---

absl-py 2.1.0
aiohttp 3.9.5
aiosignal 1.3.1
anyio 3.6.1
argon2-cffi 21.3.0
argon2-cffi-bindings 21.2.0
asttokens 2.0.5
astunparse 1.6.3
async-timeout 4.0.3
attrs 21.4.0
Babel 2.10.3
backcall 0.2.0
beautifulsoup4 4.11.1
bleach 5.0.0
brotlipy 0.7.0
cachetools 5.2.0
certifi 2021.5.30
cffi 1.14.6
chardet 4.0.0
clang 5.0
conda 4.10.3
conda-package-handling 1.7.3
cryptography 3.4.7
cycler 0.11.0
debugpy 1.6.0
decorator 5.1.1
defusedxml 0.7.1
Deprecated 1.2.14
entrypoints 0.4
executing 0.8.3
fastjsonschema 2.15.3
flatbuffers 24.3.25
fonttools 4.33.3
frozenlist 1.4.1
fsspec 2024.5.0
gast 0.4.0
gitdb 4.0.11
GitPython 3.1.43
google-auth 2.34.0
google-auth-oauthlib 1.0.0
google-pasta 0.2.0
googledrivedownloader 0.4
grpcio 1.66.1
gurobipy 10.0.3
h5py 3.1.0
idna 2.10
importlib-metadata 4.11.4
importlib-resources 5.8.0
ipykernel 6.15.0
ipython 8.4.0
ipython-genutils 0.2.0
ipywidgets 7.7.0
isodate 0.6.1
jax 0.4.13
jedi 0.18.1
Jinja2 3.1.2
joblib 1.4.2
JPype1 1.4.0
json5 0.9.8
jsonschema 4.6.0
jupyter-client 7.3.4
jupyter-core 4.10.0
jupyter-server 1.17.1
jupyterlab 3.4.3
jupyterlab-language-pack-zh-CN 3.4.post1
jupyterlab-pygments 0.2.2
jupyterlab-server 2.14.0
jupyterlab-widgets 1.1.0
keras 2.12.0
Keras-Preprocessing 1.1.2
kiwisolver 1.4.3
libclang 18.1.1
lightning-utilities 0.11.2
littleutils 0.2.2
Markdown 3.3.7
MarkupSafe 2.1.1
matplotlib 3.5.2
matplotlib-inline 0.1.3
mistune 0.8.4
ml-dtypes 0.2.0
multidict 6.0.5
nbclassic 0.3.7
nbclient 0.6.4
nbconvert 6.5.0
nbformat 5.4.0
nest-asyncio 1.5.5
networkx 3.1
notebook 6.4.12
notebook-shim 0.1.0
numpy 1.23.0
oauthlib 3.2.0
ogb 1.3.6
opt-einsum 3.3.0
outdated 0.2.2
packaging 21.3
pandas 2.0.3
pandocfilters 1.5.0
parso 0.8.3
pexpect 4.8.0
pickleshare 0.7.5
Pillow 9.1.1
pip 21.1.3
prometheus-client 0.14.1
prompt-toolkit 3.0.29
protobuf 4.25.5
pslpython 2.4.0
psutil 5.9.1
ptyprocess 0.7.0
pure-eval 0.2.2
pyasn1 0.4.8
pyasn1-modules 0.2.8
pycosat 0.6.3
pycparser 2.20
Pygments 2.12.0
pyOpenSSL 20.0.1
pyparsing 3.0.9
pyrsistent 0.18.1
PySocks 1.7.1
python-dateutil 2.8.2
python-louvain 0.16
pytz 2022.1
PyYAML 6.0.2
pyzmq 23.2.0
rdflib 7.0.0
requests 2.25.1
requests-oauthlib 1.3.1
rsa 4.8
ruamel-yaml-conda 0.15.100
scikit-learn 1.3.2
scipy 1.10.1
Send2Trash 1.8.0
setuptools 52.0.0.post20210125
six 1.15.0
smmap 5.0.1
sniffio 1.2.0
soupsieve 2.3.2.post1
stack-data 0.3.0
supervisor 4.2.4
tensorboard 2.12.3
tensorboard-data-server 0.7.2
tensorboard-plugin-wit 1.8.1
tensorflow 2.12.0
tensorflow-estimator 2.12.0
tensorflow-io-gcs-filesystem 0.34.0
termcolor 1.1.0
terminado 0.15.0
threadpoolctl 3.5.0
tinycss2 1.1.1
torch 1.11.0+cu113
torch-cluster 1.6.0
torch-geometric 2.5.3
torch-scatter 2.0.9
torch-sparse 0.6.15
torch-spline-conv 1.2.1
torchmetrics 1.4.0.post0
torchsummary 1.5.1
torchvision 0.12.0+cu113
tornado 6.1
tqdm 4.61.2
traitlets 5.3.0
typing-extensions 3.7.4.3
tzdata 2024.1
urllib3 1.26.6
wcwidth 0.2.5
webencodings 0.5.1
websocket-client 1.3.3
Werkzeug 2.1.2
wheel 0.36.2
widgetsnbextension 3.6.0
wrapt 1.12.1
yarl 1.9.4
zipp 3.8.0