hkuds / gformer

[SIGIR'2023] "GFormer: Graph Transformer for Recommendation"

Graph Transformer for Recommendation

This is the PyTorch implementation for GFormer model proposed in this paper:

Graph Transformer for Recommendation
Chaoliu Li, Lianghao Xia, Xubin Ren, Yaowen Ye, Yong Xu, Chao Huang*
SIGIR 2023

Introduction

This paper presents a novel approach to representation learning in recommender systems by integrating generative self-supervised learning with graph transformer architecture. We highlight the importance of high-quality data augmentation with relevant self-supervised pretext tasks for improving performance. Towards this end, we propose a new approach that automates the self-supervision augmentation process through a rationale-aware generative SSL that distills informative user-item interaction patterns. The proposed recommender with Graph Transformer (GFormer) that offers parameterized collaborative rationale discovery for selective augmentation while preserving global-aware user-item relationships. In GFormer, we allow the rationale-aware SSL to inspire graph collaborative filtering with task-adaptive invariant rationalization in graph transformer. The experimental results reveal that our GFormer has the capability to consistently improve the performance over baselines on different datasets. Several in-depth experiments further investigate the invariant rationale-aware augmentation from various aspects.

Environment

The codes of GFormer are implemented and tested under the following development environment:

PyTorch:

• python=3.8.13
• torch=1.9.1
• numpy=1.19.2
• scipy=1.9.0
• networkx = 2.8.6

Datasets

We utilize three datasets for evaluating GFormer: Yelp, Ifashion, and Lastfm. Note that compared to the data used in our previous works, in this work we utilize a more sparse version of the three datasets, to increase the difficulty of recommendation task. Our evaluation follows the common implicit feedback paradigm. The datasets are divided into training set, validation set and test set by 70:5:25.

Dataset	# Users	# Items	# Interactions	Interaction Density
Yelp	$42,712$	$26,822$	$182,357$	$1.6\times 10^{-4}$
Ifashion	$31,668$	$38,048$	$618,629$	$5.1\times 10^{-4}$
LastFm	$1,889$	$15,376$	$51,987$	$1.8\times 10^{-3}$

How to Run the Code

Please unzip the datasets first. Also you need to create the History/ and the Models/ directories. The command to train GFormer on the Yelp/Ifashion/Lastfm dataset is as follows. The commands specify the hyperparameter settings that generate the reported results in the paper.

• Yelp

  python Main.py --data yelp --reg 1e-4 --ssl_reg 1 --gcn 3 --ctra 1e-3 --b2 1 --pnn 1

• Ifashion

  python Main.py --data ifashion --reg 1e-5 --ssl_reg 1 --gcn 2 --ctra 1e-3 --b2 1 --pnn 1

• Lastfm

  python Main.py --data lastfm --reg 1e-4 --ssl_reg 1 --gcn 2 --ctra 1e-3 --b2 1e-6 --pnn2

Citing our paper

Please kindly cite our paper if you find this paper and the codes helpful.

@inproceedings{Li_2023, series={SIGIR ’23},
   title={Graph Transformer for Recommendation},
   url={http://dx.doi.org/10.1145/3539618.3591723},
   DOI={10.1145/3539618.3591723},
   booktitle={Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval},
   publisher={ACM},
   author={Li, Chaoliu and Xia, Lianghao and Ren, Xubin and Ye, Yaowen and Xu, Yong and Huang, Chao},
   year={2023},
   month=jul, collection={SIGIR ’23} }

gformer's Issues

关于实验的问题

你好，请问实验中的数据稀疏性和噪声的实验是怎么做的？希望你能帮我解答，感谢！

Can you please provide the preprocessing code for interaction records? It should process from a txt or csv file and save as a pkl file.

inference code

can u provide an inference code?

FileNotFoundError

Dear Author,
I am very interested in your innovative paper, but I encountered an error when running your program: FileNotFoundError:FileNotFoundError: [Errno 2] No such file or directory: './History/tem.his' .I indeed did not find it in the project files. Thank you very much for your time.

baseline复现问题

请问AutoRec这个baseline是如何复现的

请问这篇文章有上传到arXiv吗？