Official public repository of paper "Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation"

Last update: Nov 22, 2022

Related tags

Deep Learning IAGNN

Overview

Intention Adaptive Graph Neural Network (IAGNN)

This is the official repository of paper Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation.

If you found this work helpful, please kindly cite the paper as follows:

@article{cui2021intention,
  title={Intention Adaptive Graph Neural Network for Category-aware Session-based Recommendation},
  author={Cui, Chuan and Shen, Qi and Zhu, Shixuan and Pang, Yitong and Zhang, Yiming and Gao, Hanning and Wei, Zhihua},
  journal={arXiv preprint arXiv:2112.15352},
  year={2021}
}

Prerequisite

Install the dependencies by conda

dgl~=0.6.0.post1
ipdb~=0.13.9
numpy~=1.21.2
pretty_errors~=1.2.24
PyMySQL~=1.0.2
scikit_learn~=1.0.2
torch~=1.8.1
TorchSnooper~=0.8
tqdm~=4.62.3

or by pip:

pip install -r requirements.txt

Dataset

GoogleDrive BaiduPan (提取码：2jd1)

Put the downloaded *.pkl files by following this file structure:

|--dataset
   |--diginetica_x
      |--train.pkl
      |--test.pkl
   |--jdata_cd
      |--train.pkl
      |--test.pkl
   |--yc_BT_4
      |--train.pkl
      |--test.pkl
|--IAGNN	# Souce code of this repository
   |--train.py
   |--IAGNN.py
   ...

How to train

# JData
python train.py --lr=0.003 --lr_step=2 --GL=3 --dataset=jdata_cd
# Yoochoose
python train.py --lr=0.001 --lr_step=1 --GL=1 --dataset=yc_BT_4
# Diginetica
python train.py --lr=0.003 --lr_step=1 --GL=2 --dataset=diginetica_x

Official public repository of paper "Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation"

Related tags

Overview

Intention Adaptive Graph Neural Network (IAGNN)

Prerequisite

Dataset

How to train

Owner

Multiple Object Tracking with Yolov5!

MRQy is a quality assurance and checking tool for quantitative assessment of magnetic resonance imaging (MRI) data.

An example to implement a new backbone with OpenMMLab framework.

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification

A Real-Time-Strategy game for Deep Learning research

LabelImg is a graphical image annotation tool.

CRLT: A Unified Contrastive Learning Toolkit for Unsupervised Text Representation Learning

Content shared at DS-OX Meetup

Unsupervised clustering of high content screen samples

Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

Global Rhythm Style Transfer Without Text Transcriptions

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

End-to-End Object Detection with Fully Convolutional Network

Subgraph Based Learning of Contextual Embedding

OpenCV, MediaPipe Pose Estimation, Affine Transform for Icon Overlay

Official repository for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'21, Oral Presentation)

This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

An end-to-end implementation of intent prediction with Metaflow and other cool tools

PyTorch Live is an easy to use library of tools for creating on-device ML demos on Android and iOS.