Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems

Related tags

Deep LearningASMG
Overview

Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems

This is our experimental code for RecSys 2021 paper "Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems".

The paper is available here.
The video is available here.
The slide is available here.

Requirements

tensorflow 1.4.0
pandas
numpy

GPUs with memory >= 10GB

Data Preprocessing

The raw data can be obtained from:
Tmall Data data_format1
Sobazaar Data Data > Sobazaar-hashID.csv.gz
MovieLens Data ml-25m

To preprocess the above raw data, save them in the raw_data folder under the root directory, and do

cd preproc
python tmall_preproc.py
python soba_preproc.py
python ml_preproc.py

The preprocessed datasets will be saved in the datasets folder for later use.

Pretraining

To simulate the real-world applications, the first 10 periods of dataset are used to pretrain an initial Embedding&MLP base model, and all the compared model updating methods will restore from the same pretrained model.

To pretrain a model for Tmall/Sobazaar/MovieLens, do

cd Tmall/pretrain
python train_tmall.py

cd Sobazaar/pretrain
python train_soba.py

cd MovieLens/pretrain
python train_ml.py

The pretrained base model will be saved in Tmall/pretrain/ckpts, Sobazaar/pretrain/ckpts and MovieLens/pretrain/ckpts respectively.

All the hyper-parameters can be easily configured in train_config at the beginning of each entry file (i.e., train_xxx.py).

Note: pretraining must be done before conducting any model updating method.

Baselines and Variants

All the compared model updating methods for a specific dataset are contained in the folder named by that dataset.

Our proposed method:
ASMGgru_multi

Baseline methods:
IU
BU
SPMF
IncCTR
SML
SMLmf

Variants of ASMGgru_multi:
ASMGgru_zero
ASMGgru_full
ASMGgru_single
(we do not create a separate folder for ASMGgru_uniform, as it can be easily implemented in ASMGgru_multi, see the code for more details)

To perform any of the ASMGgru methods, we need to first conduct a run of IU to generate the input model sequence.

For example, to perform a run of IU experiment for Tmall, do

cd Tmall/IU
python train_tmall.py

Then we can proceed to perform any of the ASMGgru methods

cd Tmall/ASMGgru_multi
python train_tmall.py

Other model updating methods can be conducted on their own without any pre-requisite.

Note that for SMLmf, since it is based on a different base model (i.e., Matrix Factorization), additional pretraining needs to be performed for this method.

cd Tmall/SMLmf/pretrain
python train_tmall.py

Then

cd Tmall/SMLmf/SML
python train_tmall.py

All the hyper-parameters can be easily configured in train_config at the beginning of each entry file (i.e., train_xxx.py).

The evaluation results can be found from the path with the following format:

/ /ckpts/ / /test_metrics.txt

where is configured in train_config of the entry file, containing some essential hyper-parameter settings, and by default is date20141030 for Tmall and period30 for MovieLens and Sobazaar.

Here are some examples of the possible paths that the evaluation results may reside:

Tmall/ASMGgru_multi/ckpts/ASMGgru_multi_linear_train11-23_test24-30_4emb_4mlp_1epoch_3_0.01/date20141030/test_metrics.txt

MovieLens/IU/ckpts/IU_train11-23_test24-30_1epoch_0.001/period30/test_metrics.txt

Citation

If you find this repo useful in your research, please cite the following:

@inproceedings{peng2021learning,
  title={Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems},
  author={Peng, Danni and Pan, Sinno Jialin and Zhang, Jie and Zeng, Anxiang},
  booktitle={Fifteenth ACM Conference on Recommender Systems},
  pages={411--421},
  year={2021}
}
Text Extraction Formulation + Feedback Loop for state-of-the-art WSD (EMNLP 2021)

ConSeC is a novel approach to Word Sense Disambiguation (WSD), accepted at EMNLP 2021. It frames WSD as a text extraction task and features a feedback loop strategy that allows the disambiguation of

Sapienza NLP group 36 Dec 13, 2022
CONditionals for Ordinal Regression and classification in PyTorch

CONDOR pytorch implementation for ordinal regression with deep neural networks. Documentation: https://GarrettJenkinson.github.io/condor_pytorch About

7 Jul 25, 2022
Bio-OFC gym implementation and Gym-Fly environment

Bio-OFC gym implementation and Gym-Fly environment This repository includes the gym compatible implementation of the Bio-OFC algorithm from the paper

Siavash Golkar 1 Nov 16, 2021
Geometric Algebra package for JAX

JAXGA - JAX Geometric Algebra GitHub | Docs JAXGA is a Geometric Algebra package on top of JAX. It can handle high dimensional algebras by storing onl

Robin Kahlow 36 Dec 22, 2022
PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

PFENet This is the implementation of our paper PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation that has been accepted to IEE

DV Lab 230 Dec 31, 2022
Implementation of Neonatal Seizure Detection using EEG signals for deploying on edge devices including Raspberry Pi.

NeonatalSeizureDetection Description Link: https://arxiv.org/abs/2111.15569 Citation: @misc{nagarajan2021scalable, title={Scalable Machine Learn

Vishal Nagarajan 11 Nov 08, 2022
CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

CLIP-GEN [简体中文][English] 本项目在萤火二号集群上用 PyTorch 实现了论文 《CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP》。 CLIP-GEN 是一个 Language-F

75 Dec 29, 2022
Self-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)

Self-Supervised Pillar Motion Learning for Autonomous Driving Chenxu Luo, Xiaodong Yang, Alan Yuille Self-Supervised Pillar Motion Learning for Autono

QCraft 101 Dec 05, 2022
Code for the paper titled "Prabhupadavani: A Code-mixed Speech Translation Data for 25 languages"

Prabhupadavani: A Code-mixed Speech Translation Data for 25 languages Code for the paper titled "Prabhupadavani: A Code-mixed Speech Translation Data

Ayush Daksh 12 Dec 01, 2022
Goal of the project : Detecting Temporal Boundaries in Sign Language videos

MVA RecVis course final project : Goal of the project : Detecting Temporal Boundaries in Sign Language videos. Sign language automatic indexing is an

Loubna Ben Allal 6 Dec 21, 2022
Official PaddlePaddle implementation of Paint Transformer

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction [Paper] [Paddle Implementation] Update We have optimized the serial inference p

TianweiLin 284 Dec 31, 2022
Code for ACM MM2021 paper "Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection"

CTDNet The PyTorch code for ACM MM2021 paper "Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection" Requirements Python 3.6

CVTEAM 28 Oct 20, 2022
A simple consistency training framework for semi-supervised image semantic segmentation

PseudoSeg: Designing Pseudo Labels for Semantic Segmentation PseudoSeg is a simple consistency training framework for semi-supervised image semantic s

Google Interns 143 Dec 13, 2022
A Comparative Review of Recent Kinect-Based Action Recognition Algorithms (TIP2020, Matlab codes)

A Comparative Review of Recent Kinect-Based Action Recognition Algorithms This repo contains: the HDG implementation (Matlab codes) for 'Analysis and

Lei Wang 5 Oct 22, 2022
Implementation for "Exploiting Aliasing for Manga Restoration" (CVPR 2021)

[CVPR Paper](To appear) | [Project Website](To appear) | BibTex Introduction As a popular entertainment art form, manga enriches the line drawings det

133 Dec 15, 2022
Official Pytorch Implementation of: "Semantic Diversity Learning for Zero-Shot Multi-label Classification"(2021) paper

Semantic Diversity Learning for Zero-Shot Multi-label Classification Paper Official PyTorch Implementation Avi Ben-Cohen, Nadav Zamir, Emanuel Ben Bar

28 Aug 29, 2022
Code for Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations

Implementation for Iso-Points (CVPR 2021) Official code for paper Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations paper |

Yifan Wang 66 Nov 08, 2022
PyTorch 1.0 inference in C++ on Windows10 platforms

Serving PyTorch Models in C++ on Windows10 platforms How to use Prepare Data examples/data/train/ - 0 - 1 . . . - n examples/data/test/

Henson 88 Oct 15, 2022
Fiddle is a Python-first configuration library particularly well suited to ML applications.

Fiddle Fiddle is a Python-first configuration library particularly well suited to ML applications. Fiddle enables deep configurability of parameters i

Google 227 Dec 26, 2022
PyTorch implementation for View-Guided Point Cloud Completion

PyTorch implementation for View-Guided Point Cloud Completion

22 Jan 04, 2023