Light

yangji9181 / pace2017 Goto Github PK

View Code? Open in Web Editor NEW

72.0 2.0 31.0 11 KB

A step-by-step Keras implementation of PACE (Preference And Context Embedding) described in our KDD 2017 paper.

Python 59.38% Jupyter Notebook 40.62%

pace2017's Introduction

Implementation of PACE, KDD 2017.

Please cite the following work if you find the code useful.

@inproceedings{yang2017bridging,
	Author = {Yang, Carl and Bai, Lanxiao and Zhang, Chao and Yuan, Quan and Han, Jiawei},
	Booktitle = {KDD},
	Title = {Bridging collaborative filtering and semi-supervised learning: a neural approach for poi recommendation},
	Year = {2017}
}

Contact: Carl Yang ([email protected])

Usage:

To run the code, you need to have Python3 and iPython Notebook installed.

Visit https://snap.stanford.edu/data/loc-gowalla.html or https://www.yelp.com/dataset/challenge to download the Gowalla or Yelp datasets. Please refer to dataset.py the paper for data preprocessing.
Start iPython Notebook Server ipython3 notebook and sequentially run cells in train.ipynb

If you are using remote machine, you can:

Start iPython Notebook Server on remote machine: ipython notebook --no-browser --port=8889
Redirect ssh connection to localhost ssh -N -f -L localhost:8880:localhost:8889 <user>@<host>
Open browser and go to <user>@<host>:8880

pace2017's People

Contributors

Stargazers

Watchers

pace2017's Issues

About dataset

I'm a student who am learning POI recommendation. I tried to run your program and I had download your gowalla dataset file from http://lbai5.web.engr.illinois.edu/data/ . But I find it is different from the dataset on http://snap.stanford.edu/data/loc-gowalla.html (you reference it's corresponding paper in your paper when you mention the gowalla dataset ) . One of the differences is the number of location, 2942667 in the former dataset(spot_location.txt) and 1280969 in the latter. Why dose that happen?

Missing Dataset

Can you add a link where we can download the dataset, which increases the citation of your paper? because we want to mention your paper but your code doesn't work.

Some errors in scripts

I find some errors in your scripts.
First one is in download_data.sh(#9 and #12).
Running this scipt will download visited_spots.txt twice.

Second one is in dataset.py(#300).
The code path.append(graph_dict.keys()[random.randrange(len(graph_dict))]) will cause some exceptions using python3.6.

Dataset unavailable

http://lbai5.web.engr.illinois.edu has been suspended, so the Gowalla dataset is unavailable.

In addition, there is no indication on how the Yelp dataset is preprocessed, since dataset.py seems to be coded specifically for the Gowalla dataset.

Baselines

Hello,
could you possibly also share the code of the baselines that you used in the paper:
Bridging Collaborative Filtering and Semi-Supervised Learning:
A Neural Approach for POI Recommendation

Thank you

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.