Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

Related tags

Deep LearningGRCN
Overview

Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

This is our Pytorch implementation for the paper:

Yinwei Wei, Xiang Wang, Liqiang Nie, Xiangnan He and Tat-Seng Chua. Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback. In ACM MM`20, Seattle, United States, Oct. 12-16, 2020
Author: Dr. Yinwei Wei (weiyinwei at hotmail.com)

Introduction

In this work, we focus on adaptively refining the structure of interaction graph to discover and prune potential false-positive edges. Towards this end, we devise a new GCN-based recommendermodel, Graph-Refined Convolutional Network(GRCN), which adjusts the structure of interaction graph adaptively based on status of mode training, instead of remaining the fixed structure.

Environment Requirement

The code has been tested running under Python 3.5.2. The required packages are as follows:

  • Pytorch == 1.4.0
  • torch-cluster == 1.4.2
  • torch-geometric == 1.2.1
  • torch-scatter == 1.2.0
  • torch-sparse == 0.4.0
  • numpy == 1.16.0

Example to Run the Codes

The instruction of commands has been clearly stated in the codes.

  • Kwai dataset
    python main.py --l_r=0.0001 --weight_decay=0.1 --dropout=0 --weight_mode=confid --num_routing=3 --is_pruning=False --data_path=Kwai --has_a=False --has_t=False
  • Tiktok dataset
    python main.py --l_r=0.0001 --weight_decay=0.001 --dropout=0 --weight_mode=confid --num_routing=3 --is_pruning=False --data_path=Tiktok
  • Movielens dataset
    python main.py --l_r=0.0001 --weight_decay=0.0001 --dropout=0 --weight_mode=confid --num_routing=3 --is_pruning=False

Some important arguments:

  • weight_model It specifics the type of multimodal correlation integration. Here we provide three options:

    1. mean implements the mean integration without confidence vectors. Usage --weight_model 'mean'
    2. max implements the max integration without confidence vectors. Usage --weight_model 'max'
    3. confid (by default) implements the max integration with confidence vectors. Usage --weight_model 'confid'
  • fusion_mode It specifics the type of user and item representation in the prediction layer. Here we provide three options:

    1. concat (by default) implements the concatenation of multimodal features. Usage --fusion_mode 'concat'
    2. mean implements the mean pooling of multimodal features. Usage --fusion_mode 'max'
    3. id implements the representation with only the id embeddings. Usage --fusion_mode 'id'
  • is_pruning It specifics the type of pruning operation. Here we provide three options:

    1. Ture (by default) implements the hard pruning operations. Usage --is_pruning 'True'
    2. False implements the soft pruning operations. Usage --is_pruning 'False'
  • 'has_v', 'has_a', and 'has_t' indicate the modality used in the model.

Dataset

Please check MMGCN for the datasets: Kwai, Tiktok, and Movielens.

Due to the copyright, we could only provide some toy datasets for validation. If you need the complete ones, please contact the owners of the datasets.

#Interactions #Users #Items Visual Acoustic Textual
Movielens 1,239,508 55,485 5,986 2,048 128 100
Tiktok 726,065 36,656 76,085 128 128 128
Kwai 298,492 86,483 7,010 2,048 - -

-train.npy Train file. Each line is a user with her/his positive interactions with items: (userID and micro-video ID)
-val.npy Validation file. Each line is a user with her/his several positive interactions with items: (userID and micro-video ID)
-test.npy Test file. Each line is a user with her/his several positive interactions with items: (userID and micro-video ID)

Owner
Thank you for your attention. If you have any questions, please email me.
Mmrotate - OpenMMLab Rotated Object Detection Benchmark

OpenMMLab website HOT OpenMMLab platform TRY IT OUT 📘 Documentation | 🛠️ Insta

OpenMMLab 1.2k Jan 04, 2023
Deep deconfounded recommender (Deep-Deconf) for paper "Deep causal reasoning for recommendations"

Deep Causal Reasoning for Recommender Systems The codes are associated with the following paper: Deep Causal Reasoning for Recommendations, Yaochen Zh

Yaochen Zhu 22 Oct 15, 2022
A collection of Jupyter notebooks to play with NVIDIA's StyleGAN3 and OpenAI's CLIP for a text-based guided image generation.

StyleGAN3 CLIP-based guidance StyleGAN3 + CLIP StyleGAN3 + inversion + CLIP This repo is a collection of Jupyter notebooks made to easily play with St

Eugenio Herrera 176 Dec 30, 2022
Rank 3 : Source code for OPPO 6G Data Generation Challenge

OPPO 6G Data Generation with an E2E Framework Homepage of OPPO 6G Data Generation Challenge Datasets H1_32T4R.mat H2_32T4R.mat Please put the original

Sen Pei 97 Jan 07, 2023
Empowering journalists and whistleblowers

Onymochat Empowering journalists and whistleblowers Onymochat is an end-to-end encrypted, decentralized, anonymous chat application. You can also host

Samrat Dutta 19 Sep 02, 2022
MoveNetを用いたPythonでの姿勢推定のデモ

MoveNet-Python-Example MoveNetのPythonでの動作サンプルです。 ONNXに変換したモデルも同梱しています。変換自体を試したい方はMoveNet_tf2onnx.ipynbを使用ください。 2021/08/24時点でTensorFlow Hubで提供されている以下モデ

KazuhitoTakahashi 38 Dec 17, 2022
PyTorch implementation for 3D human pose estimation

Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach This repository is the PyTorch implementation for the network presented in:

Xingyi Zhou 579 Dec 22, 2022
Official implementation of Pixel-Level Bijective Matching for Video Object Segmentation

BMVOS This is the official implementation of Pixel-Level Bijective Matching for Video Object Segmentation, to appear in WACV 2022. @article{cho2021pix

Suhwan Cho 13 Dec 14, 2022
Graph WaveNet apdapted for brain connectivity analysis.

Graph WaveNet for brain network analysis This is the implementation of the Graph WaveNet model used in our manuscript: S. Wein , A. Schüller, A. M. To

4 Dec 17, 2022
Implementation of "Scaled-YOLOv4: Scaling Cross Stage Partial Network" using PyTorch framwork.

YOLOv4-large This is the implementation of "Scaled-YOLOv4: Scaling Cross Stage Partial Network" using PyTorch framwork. YOLOv4-CSP YOLOv4-tiny YOLOv4-

Kin-Yiu, Wong 2k Jan 02, 2023
ThunderGBM: Fast GBDTs and Random Forests on GPUs

Documentations | Installation | Parameters | Python (scikit-learn) interface What's new? ThunderGBM won 2019 Best Paper Award from IEEE Transactions o

Xtra Computing Group 647 Jan 04, 2023
A framework for joint super-resolution and image synthesis, without requiring real training data

SynthSR This repository contains code to train a Convolutional Neural Network (CNN) for Super-resolution (SR), or joint SR and data synthesis. The met

83 Jan 01, 2023
EASY - Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients.

EASY - Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients. This repository is the official im

Yassir BENDOU 57 Dec 26, 2022
Deep Learning Theory

Deep Learning Theory 整理了一些深度学习的理论相关内容,持续更新。 Overview Recent advances in deep learning theory 总结了目前深度学习理论研究的六个方向的一些结果,概述型,没做深入探讨(2021)。 1.1 complexity

fq 103 Jan 04, 2023
FewBit — a library for memory efficient training of large neural networks

FewBit FewBit — a library for memory efficient training of large neural networks. Its efficiency originates from storage optimizations applied to back

24 Oct 22, 2022
A Deep Learning Framework for Neural Derivative Hedging

NNHedge NNHedge is a PyTorch based framework for Neural Derivative Hedging. The following repository was implemented to ease the experiments of our pa

GUIJIN SON 17 Nov 14, 2022
Code accompanying the paper "ProxyFL: Decentralized Federated Learning through Proxy Model Sharing"

ProxyFL Code accompanying the paper "ProxyFL: Decentralized Federated Learning through Proxy Model Sharing" Authors: Shivam Kalra*, Junfeng Wen*, Jess

Layer6 Labs 14 Dec 06, 2022
Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt. This is done by

Mehdi Cherti 135 Dec 30, 2022
A robotic arm that mimics hand movement through MediaPipe tracking.

La-Z-Arm A robotic arm that mimics hand movement through MediaPipe tracking. Hardware NVidia Jetson Nano Sparkfun Pi Servo Shield Micro Servos Webcam

Alfred 1 Jun 05, 2022
A PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).

CapsGNN ⠀⠀ A PyTorch implementation of Capsule Graph Neural Network (ICLR 2019). Abstract The high-quality node embeddings learned from the Graph Neur

Benedek Rozemberczki 1.2k Jan 02, 2023