Official implementation of SIGIR'2021 paper: "Sequential Recommendation with Graph Neural Networks".

Last update: Dec 26, 2022

Overview

SURGE: Sequential Recommendation with Graph Neural Networks

This is our TensorFlow implementation for the paper:

Sequential Recommendation with Graph Neural Networks. SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.

Please cite our paper if you use this repository.

@inproceedings{chang2021sequential,
  title={Sequential Recommendation with Graph Neural Networks},
  author={Chang, Jianxin and Gao, Chen and Zheng, Yu and Hui, Yiqun and Niu, Yanan and Song, Yang and Jin, Depeng and Li, Yong},
  booktitle={Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  pages={378--387},
  year={2021}
}

The code is tested under a Linux desktop with TensorFlow 1.12.3 and Python 3.6.8.

Data Pre-processing

The script is reco_utils/dataset/sequential_reviews.py which will be automatically excuted when there exists no pre-processed training file.

Model Training

To train our model on Kuaishou dataset (with default hyper-parameters):

python examples/00_quick_start/sequential.py --dataset kuaishou

or on Taobao dataset:

python examples/00_quick_start/sequential.py --dataset taobao

Misc

The implemention is based on Microsoft Recommender.

Official implementation of SIGIR'2021 paper: "Sequential Recommendation with Graph Neural Networks".

Related tags

Overview

SURGE: Sequential Recommendation with Graph Neural Networks

Data Pre-processing

Model Training

Misc

Owner

FIB LAB, Tsinghua University

Digital Twin Mobility Profiling: A Spatio-Temporal Graph Learning Approach

TJU Deep Learning & Neural Network

HiFT: Hierarchical Feature Transformer for Aerial Tracking (ICCV2021)

Flaxformer: transformer architectures in JAX/Flax

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

Official repository for Automated Learning Rate Scheduler for Large-Batch Training (8th ICML Workshop on AutoML)

Facial expression detector

g9.py - Torch interactive graphics

Code, pre-trained models and saliency results for the paper "Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images".

SAFL: A Self-Attention Scene Text Recognizer with Focal Loss

Code-free deep segmentation for computational pathology

Tensorflow Implementation for "Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition"

EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers

Code of our paper "Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning"

Supervised 3D Pre-training on Large-scale 2D Natural Image Datasets for 3D Medical Image Analysis

A robust camera and Lidar fusion based velocity estimator to undistort the pointcloud.

Implementation of CVPR'2022:Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Chainer implementation of recent GAN variants

[NeurIPS-2021] Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation

This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their coordinates and detected labels.