update env and readme

README.md

@@ -1,5 +1,5 @@
 # Introduction 
-This is the repository of our accepted CIKM 2021 paper "Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer" and the proposed model is TGSRec. Paper is available on [arxiv](https://arxiv.org/abs/2108.06625)
+This is the repository of our accepted CIKM 2021 paper "Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer" and the proposed model is TGSRec. Paper is available on [arxiv](https://arxiv.org/abs/2108.06625). This work focuses on multi-steps continuous-time recommendation, where user and item embeddings are generated in any unseen future timestamps. Different from existing sequential recommendation methods, which are optimized for next-item prediction, this work is learned for recommendation in any timestamps.
 
 # Citation
 Please cite our paper if using this code. 
@@ -14,4 +14,15 @@ Please cite our paper if using this code.
 ```
 
 # Implementation
-TO BE CONTINUED
+
+The code is implemented based on [TGAT](https://github.com/StatsDLMathsRecomSys/Inductive-representation-learning-on-temporal-graphs).
+
+## Environment Setup
+The code is tested under a Linux desktop (w/ GTX 1080 Ti GPU) with TensorFlow 1.12 and Python 3.6.
+Create the requirement with the requirements.txt
+
+## ML-100K Dataset Execution
+### Sample code to run
+```
+python run_TGREC.py -d ml-100k --uniform --bs 600 --lr 0.001 --n_degree 30 --agg_method attn --attn_mode prod --gpu 0 --n_head 2 --n_layer 2 --prefix Video_Games_bce --node_dim 32 --time_dim 32 --drop_out 0.3 --reg 0.3 --negsampleeval 1000
+```

requirements.txt

@@ -0,0 +1,154 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: linux-64
+_libgcc_mutex=0.1=main
+aiocache=0.11.1=pypi_0
+aiofiles=0.5.0=pypi_0
+aiohttp=3.6.2=pypi_0
+aiopubsub=2.1.5=pypi_0
+aioredis=1.3.1=pypi_0
+aiosmtplib=1.1.2=pypi_0
+alembic=1.3.3=pypi_0
+aniso8601=7.0.0=pypi_0
+apscheduler=3.6.3=pypi_0
+ase=3.20.1=pypi_0
+async-timeout=3.0.1=pypi_0
+attrs=20.1.0=pypi_0
+ax=0.48.0=pypi_0
+ax-platform=0.1.14=pypi_0
+blas=1.0=mkl
+blessings=1.7=pypi_0
+botorch=0.3.0=pypi_0
+ca-certificates=2020.12.8=h06a4308_0
+certifi=2020.12.5=py37h06a4308_0
+cffi=1.14.0=py37h2e261b9_0
+chardet=3.0.4=pypi_0
+cudatoolkit=10.0.130=0
+cycler=0.10.0=pypi_0
+docopt=0.6.2=pypi_0
+dotmap=1.3.8=pypi_0
+freetype=2.9.1=h8a8886c_1
+future=0.18.2=pypi_0
+googledrivedownloader=0.4=pypi_0
+gpustat=0.6.0=pypi_0
+gpytorch=1.2.0=pypi_0
+graphene=2.1.8=pypi_0
+graphene-sqlalchemy=2.2.2=pypi_0
+graphql-core=2.2.1=pypi_0
+graphql-relay=2.0.0=pypi_0
+graphql-server-core=2.0.0=pypi_0
+graphql-ws=0.3.0=pypi_0
+gunicorn=20.0.4=pypi_0
+h11=0.8.1=pypi_0
+h2=3.2.0=pypi_0
+h5py=2.10.0=pypi_0
+hiredis=1.1.0=pypi_0
+hpack=3.0.0=pypi_0
+hstspreload=2020.8.25=pypi_0
+httptools=0.1.1=pypi_0
+httpx=0.9.3=pypi_0
+hyperframe=5.2.0=pypi_0
+idna=2.10=pypi_0
+importlib-metadata=4.5.0=pypi_0
+intel-openmp=2020.0=166
+isodate=0.6.0=pypi_0
+jinja2=2.11.2=pypi_0
+joblib=0.14.1=pypi_0
+jpeg=9b=h024ee3a_2
+kiwisolver=1.2.0=pypi_0
+ld_impl_linux-64=2.33.1=h53a641e_7
+libedit=3.1.20181209=hc058e9b_0
+libffi=3.2.1=hd88cf55_4
+libgcc-ng=9.1.0=hdf63c60_0
+libgfortran-ng=7.3.0=hdf63c60_0
+libpng=1.6.37=hbc83047_0
+libstdcxx-ng=9.1.0=hdf63c60_0
+libtiff=4.1.0=h2733197_0
+llvmlite=0.33.0=pypi_0
+lmdb=1.0.0=pypi_0
+loguru=0.4.1=pypi_0
+mako=1.1.3=pypi_0
+markdown2=2.3.8=pypi_0
+markupsafe=1.1.1=pypi_0
+matplotlib=3.3.1=pypi_0
+mkl=2020.0=166
+mkl-service=2.3.0=py37he904b0f_0
+mkl_fft=1.0.15=py37ha843d7b_0
+mkl_random=1.1.0=py37hd6b4f25_0
+multidict=4.7.6=pypi_0
+ncurses=6.2=he6710b0_0
+networkx=2.4=pypi_0
+ninja=1.9.0=py37hfd86e86_0
+numba=0.50.1=pypi_0
+numpy=1.16.4=pypi_0
+numpy-base=1.18.1=py37hde5b4d6_1
+nvidia-ml-py3=7.352.0=pypi_0
+olefile=0.46=py_0
+openssl=1.1.1i=h27cfd23_0
+packaging=20.1=pypi_0
+pandas=0.24.2=pypi_0
+passlib=1.7.2=pypi_0
+pillow=7.2.0=pypi_0
+pip=20.3.3=py37h06a4308_0
+plotly=4.9.0=pypi_0
+prettytable=2.1.0=pypi_0
+promise=2.3=pypi_0
+protobuf=3.19.1=pypi_0
+py-postgresql=1.2.1=pypi_0
+pycparser=2.20=py_0
+pyjwt=1.7.1=pypi_0
+pyparsing=2.4.7=pypi_0
+pytest-runner=5.2=pypi_0
+python=3.7.7=hcf32534_0_cpython
+python-editor=1.0.4=pypi_0
+pyyaml=5.1.2=pypi_0
+rdflib=5.0.0=pypi_0
+readline=8.0=h7b6447c_0
+requests=2.24.0=pypi_0
+retrying=1.3.3=pypi_0
+rfc3986=1.4.0=pypi_0
+rsa=4.0=pypi_0
+ruamel-yaml=0.16.7=pypi_0
+ruamel-yaml-clib=0.2.0=pypi_0
+rx=1.6.1=pypi_0
+sanic=19.12.2=pypi_0
+sanic-compress=0.1.1=pypi_0
+sanic-cors=0.9.9.post4=pypi_0
+sanic-graphql=1.1.0=pypi_0
+sanic-jwt=1.4.0=pypi_0
+sanic-plugins-framework=0.9.3=pypi_0
+scikit-learn=0.22.1=pypi_0
+scipy=1.4.1=pypi_0
+setuptools=46.1.3=py37_0
+simplejson=3.17.3=pypi_0
+singledispatch=3.4.0.3=pypi_0
+six=1.14.0=py37_0
+sniffio=1.1.0=pypi_0
+sqlalchemy=1.3.13=pypi_0
+sqlalchemy-utils=0.36.1=pypi_0
+sqlite=3.31.1=h7b6447c_0
+stripe=2.42.0=pypi_0
+tensorboardx=2.4.1=pypi_0
+tk=8.6.8=hbc83047_0
+torch=1.6.0=pypi_0
+torch-cluster=1.5.7=pypi_0
+torch-geometric=1.6.1=pypi_0
+torch-scatter=2.0.5=pypi_0
+torch-sparse=0.6.7=pypi_0
+torch-spline-conv=1.2.0=pypi_0
+torchfm=0.7.0=pypi_0
+torchvision=0.3.0=py37_cu10.0.130_1
+tqdm=4.41.1=pypi_0
+typing-extensions=3.7.4.3=pypi_0
+tzlocal=2.1=pypi_0
+ujson=3.1.0=pypi_0
+urllib3=1.25.10=pypi_0
+uvloop=0.14.0=pypi_0
+wcwidth=0.2.5=pypi_0
+websockets=8.1=pypi_0
+wheel=0.34.2=py37_0
+xz=5.2.4=h14c3975_4
+yarl=1.5.1=pypi_0
+zipp=3.4.1=pypi_0
+zlib=1.2.11=h7b6447c_3
+zstd=1.3.7=h0b5b093_0