GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → Ocxs → THACIL

Ocxs / THACIL

Licence: other
Temporal Hierarchical Attention at Category- and Item-Level for Micro-Video Click-Through Prediction

Programming Languages

python
139335 projects - #7 most used programming language

Labels

recommendation

Projects that are alternatives of or similar to THACIL

EATNN
This is our implementation of EATNN: Efficient Adaptive Transfer Neural Network (SIGIR 2019)
Stars: ✭ 23 (-4.17%)
Mutual labels:  recommendation
Surprise
A Python scikit for building and analyzing recommender systems
Stars: ✭ 5,151 (+21362.5%)
Mutual labels:  recommendation
Machine-Learning
Examples of all Machine Learning Algorithm in Apache Spark
Stars: ✭ 15 (-37.5%)
Mutual labels:  recommendation
MetaHeac
This is an official implementation for "Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising"(KDD2021).
Stars: ✭ 36 (+50%)
Mutual labels:  recommendation
larafy
Larafy is a Laravel package for Spotify API. It is more like a wrapper for the Spotify API.
Stars: ✭ 53 (+120.83%)
Mutual labels:  recommendation
Reco Papers
Classic papers and resources on recommendation
Stars: ✭ 2,804 (+11583.33%)
Mutual labels:  recommendation
tutorials
A tutorial series by Preferred.AI
Stars: ✭ 136 (+466.67%)
Mutual labels:  recommendation
GNN-Recommender-Systems
An index of recommendation algorithms that are based on Graph Neural Networks.
Stars: ✭ 505 (+2004.17%)
Mutual labels:  recommendation
Deepctr
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
Stars: ✭ 5,686 (+23591.67%)
Mutual labels:  recommendation
Recommendation-based-on-sequence-
Recommendation based on sequence
Stars: ✭ 23 (-4.17%)
Mutual labels:  recommendation
Movie Recommendation Engine
Movie Recommender based on the MovieLens Dataset (ml-100k) using item-item collaborative filtering.
Stars: ✭ 21 (-12.5%)
Mutual labels:  recommendation
netflix-style-recommender
A simple movie recommendation engine
Stars: ✭ 65 (+170.83%)
Mutual labels:  recommendation
LR-GCCF
Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach, AAAI2020
Stars: ✭ 99 (+312.5%)
Mutual labels:  recommendation
reading-list
My reading list
Stars: ✭ 15 (-37.5%)
Mutual labels:  recommendation
NARRE
This is our implementation of NARRE:Neural Attentional Regression with Review-level Explanations
Stars: ✭ 100 (+316.67%)
Mutual labels:  recommendation
WSDM2022-PTUPCDR
This is the official implementation of our paper Personalized Transfer of User Preferences for Cross-domain Recommendation (PTUPCDR), which has been accepted by WSDM2022.
Stars: ✭ 65 (+170.83%)
Mutual labels:  recommendation
Recommenders
Best Practices on Recommendation Systems
Stars: ✭ 11,818 (+49141.67%)
Mutual labels:  recommendation
SAMN
This is our implementation of SAMN: Social Attentional Memory Network
Stars: ✭ 45 (+87.5%)
Mutual labels:  recommendation
eTrust
Source code and dataset for TKDE 2019 paper “Trust Relationship Prediction in Alibaba E-Commerce Platform”
Stars: ✭ 14 (-41.67%)
Mutual labels:  recommendation
disentangled graph collaborative filtering
Disentagnled Graph Collaborative Filtering, SIGIR2020
Stars: ✭ 118 (+391.67%)
Mutual labels:  recommendation
View All Similar Projects ➔

THACIL Network

This repo is our implementation for paper: Temporal Hierarchical Attention at Category- and Item-Level for Micro-Video Click-Through Prediction

Please cite our MM'18 paper if you use our codes. Thanks!

@inproceedings{chen2018thacil,
  title={Temporal Hierarchical Attention at Category- and Item-Level for Micro-Video Click-Through Prediction},
  author={Chen, Xusong and Liu, Dong and Zha, Zheng-Jun and Zhou, Wengang and Xiong, Zhiwei and Li, Yan},
  booktitle={MM},
  year={2018}
}

Environment Setting

  • Python 3.6 (Anaconda3)
  • Tensorflow 1.4

Usage

Download dataset and preprocess

  • Step 1: Download our dataset, named MicroVideo-1.7M (password: ms7x), which has 12,737,619 interactions that 10,986 users have made on 1,704,880 micro-videos. And move it to data/input/ folder.
  • Step 2: Generate intermediate file for training, and move it to data/input/ folder.
    • Generate user_click_ids.npy: 
      python generate_data.py --train-data-path ../../data/input/train_data.csv --save-path ../../data/input/

Training and Evaluation

  • Training
cd src
python launcher.py  --phase train
  • Evaluation
cd src
python launcher.py  --phase test

Acknowledgements

Some implementations consult the ATRank, and DiSAN.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].