Skip to content

KnowSite: Leveraging Urban Knowledge Graph for Site Selection

Notifications You must be signed in to change notification settings

tsinghua-fib-lab/UrbanKG-KnowSite

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

KnowSite: Leveraging Urban Knowledge Graph for Site Selection

"The Comparison of Data-driven Paradigm and Knowledge-driven Paradigm for Site Selection"

Requirements

To install requirements:

python 3.7.4
pytorch 1.1
dgl 0.5.1
mlflow 1.12.1

Running a model

To train (and evaluate) the model in the paper, run this command:

python main.py --dataset beijing --batch_size 128 --edim 64 --lr 0.001 --dr 0.995 --comp_opn rnn --dr 0.995 --freeze true --gcn_dropout 0.3 --kg_name kg --n_layer 2 --opn rotate --pretrain true --psa_alpha 0.5
python main.py --dataset shanghai --batch_size 128 --edim 64 --lr 0.003 --dr 0.995 --comp_opn rnn --dr 0.995 --freeze true --gcn_dropout 0.1 --kg_name kg --n_layer 2 --opn rotate --pretrain true --psa_alpha 0.8

Reference

@inproceddings{liu2023knowsite,
title 	  = {KnowSite: Leveraging Urban Knowledge Graph for Site Selection},
author	  = {Liu, Yu and Ding, Jingtao and Li, Yong},
booktitle = {ACM SIGSPATIAL},
year      = {2023}}

Releases

No releases published

Packages

No packages published

Languages