Home

Awesome

Update

2020-09:


LightGCN-pytorch

This is the Pytorch implementation for our SIGIR 2020 paper:

SIGIR 2020. Xiangnan He, Kuan Deng ,Xiang Wang, Yan Li, Yongdong Zhang, Meng Wang(2020). LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation, Paper in arXiv.

Author: Prof. Xiangnan He (staff.ustc.edu.cn/~hexn/)

(Also see Tensorflow implementation)

Introduction

In this work, we aim to simplify the design of GCN to make it more concise and appropriate for recommendation. We propose a new model named LightGCN,including only the most essential component in GCN—neighborhood aggregation—for collaborative filtering

Enviroment Requirement

pip install -r requirements.txt

Dataset

We provide three processed datasets: Gowalla, Yelp2018 and Amazon-book and one small dataset LastFM.

see more in dataloader.py

An example to run a 3-layer LightGCN

run LightGCN on Gowalla dataset:

cd code && python main.py --decay=1e-4 --lr=0.001 --layer=3 --seed=2020 --dataset="gowalla" --topks="[20]" --recdim=64

...
======================
EPOCH[5/1000]
BPR[sample time][16.2=15.84+0.42]
[saved][[BPR[aver loss1.128e-01]]
[0;30;43m[TEST][0m
{'precision': array([0.03315359]), 'recall': array([0.10711388]), 'ndcg': array([0.08940792])}
[TOTAL TIME] 35.9975962638855
...
======================
EPOCH[116/1000]
BPR[sample time][16.9=16.60+0.45]
[saved][[BPR[aver loss2.056e-02]]
[TOTAL TIME] 30.99874997138977
...

NOTE:

  1. Even though we offer the code to split user-item matrix for matrix multiplication, we strongly suggest you don't enable it since it will extremely slow down the training speed.
  2. If you feel the test process is slow, try to increase the testbatch and enable multicore(Windows system may encounter problems with multicore option enabled)
  3. Use tensorboard option, it's good.
  4. Since we fix the seed(--seed=2020 ) of numpy and torch in the beginning, if you run the command as we do above, you should have the exact output log despite the running time (check your output of epoch 5 and epoch 116).

Extend:

Results

all metrics is under top-20

pytorch version results (stop at 1000 epochs):

(for seed=2020)

Recallndcgprecision
layer=10.16870.14170.05106
layer=20.17860.15240.05456
layer=30.18240.15470.05589
layer=40.18250.15370.05576
Recallndcgprecision
layer=10.056040.045570.02519
layer=20.059880.049560.0271
layer=30.063470.052380.0285
layer=40.065150.053250.02917