Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/easezyc/Multitask-Recommendation-Library

MTReclib provides a PyTorch implementation of multi-task recommendation models and common datasets.
https://github.com/easezyc/Multitask-Recommendation-Library

advertising ctr-prediction multitask-learning multitask-recommendation recommendation recommender-system transfer-learning

Last synced: 6 months ago
JSON representation

MTReclib provides a PyTorch implementation of multi-task recommendation models and common datasets.

Awesome Lists containing this project

README 

        
# Multi-task Recommendation in PyTorch

[![MIT License](https://img.shields.io/badge/license-MIT-green.svg)](https://opensource.org/licenses/MIT)  [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)



![MTRec](./mtreclib.png)



-------------------------------------------------------------------------------



## Introduction

MTReclib provides a PyTorch implementation of multi-task recommendation models and common datasets. Currently, we implmented 7 multi-task recommendation models to enable fair comparison and boost the development of multi-task recommendation algorithms. The currently supported algorithms include:

* SingleTask：Train one model for each task, respectively

* Shared-Bottom: It is a traditional multi-task model with a shared bottom and multiple towers.

* OMoE: [Adaptive Mixtures of Local Experts](https://ieeexplore.ieee.org/abstract/document/6797059) (Neural Computation 1991)

* MMoE: [Modeling Task Relationships in Multi-task Learning with Multi-Gate Mixture-of-Experts](https://dl.acm.org/doi/pdf/10.1145/3219819.3220007) (KDD 2018)

* PLE: [Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations](https://dl.acm.org/doi/pdf/10.1145/3383313.3412236?casa_token=8fchWD8CHc0AAAAA:2cyP8EwkhIUlSFPRpfCGHahTddki0OEjDxfbUFMkXY5fU0FNtkvRzmYloJtLowFmL1en88FRFY4Q) (RecSys 2020 best paper)

* AITM: [Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising](https://dl.acm.org/doi/pdf/10.1145/3447548.3467071?casa_token=5YtVOYjJClUAAAAA:eVczwdynmE9dwoyElCG4da9fC5gsRiyX6zKt0_mIJF1K8NkU-SlNkGmpAu0c0EHbM3hBUe3zZc-o) (KDD 2021)

* MetaHeac: [Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising](https://easezyc.github.io/data/kdd21_metaheac.pdf) (KDD 2021)



## Datasets

* AliExpressDataset: This is a dataset gathered from real-world traffic logs of the search system in AliExpress. This dataset is collected from 5 countries: Russia, Spain, French, Netherlands, and America, which can utilized as 5 multi-task datasets. [Original_dataset](https://tianchi.aliyun.com/dataset/dataDetail?dataId=74690) [Processed_dataset Google Drive](https://drive.google.com/drive/folders/1F0TqvMJvv-2pIeOKUw9deEtUxyYqXK6Y?usp=sharing) [Processed_dataset Baidu Netdisk](https://pan.baidu.com/s/1AfXoJSshjW-PILXZ6O19FA?pwd=4u0r)



> For the processed dataset, you should directly put the dataset in './data/' and unpack it. For the original dataset, you should put it in './data/' and run 'python preprocess.py --dataset_name NL'.



## Requirements

* Python 3.6

* PyTorch > 1.10

* pandas

* numpy

* tqdm



## Run



Parameter Configuration:



- dataset_name: choose a dataset in ['AliExpress_NL', 'AliExpress_FR', 'AliExpress_ES', 'AliExpress_US'], default for `AliExpress_NL`

- dataset_path: default for `./data`

- model_name: choose a model in ['singletask', 'sharedbottom', 'omoe', 'mmoe', 'ple', 'aitm', 'metaheac'], default for `metaheac`

- epoch: the number of epochs for training, default for `50`

- task_num: the number of tasks, default for `2` (CTR & CVR)

- expert_num: the number of experts for ['omoe', 'mmoe', 'ple', 'metaheac'], default for `8`

- learning_rate: default for `0.001`

- batch_size: default for `2048`

- weight_decay: default for `1e-6`

- device: the device to run the code, default for `cuda:0`

- save_dir: the folder to save parameters, default for `chkpt`



You can run a model through:



```powershell

python main.py --model_name metaheac --num_expert 8 --dataset_name AliExpress_NL

```



## Results

> For fair comparisons, the learning rate is 0.001, the dimension of embeddings is 128, and mini-batch size is 2048 equally for all models. We report the mean AUC and Logloss over five random runs. Best results are in boldface.



	

		

      Methods

			AliExpress (Netherlands, NL)

			AliExpress (Spain, ES)

		

		

			CTR

      CTCVR

	  CTR

      CTCVR

		

		

			AUC

			Logloss

			AUC

      Logloss

	  AUC

			Logloss

			AUC

      Logloss

		

	

	

		

			SingleTask

			0.7222 

			0.1085

			0.8590

      0.00609

	  0.7266

			0.1207

			0.8855

      0.00456

		

    

			Shared-Bottom

			0.7228

			0.1083

			0.8511

      0.00620

	  0.7287

			0.1204

			0.8866

      0.00452

		

    

			OMoE

			0.7254

			0.1081

			0.8611

      0.00614

	  0.7253

			0.1209

			0.8859

      0.00452

		

    

			MMoE

			0.7234

			0.1080

			0.8606

      0.00607

	  0.7285

			0.1205

			0.8898

      0.00450

		

    

			PLE

			0.7292

			0.1088

			0.8591

      0.00631

			0.7273

			0.1223

			0.8913

      0.00461

		

    

			AITM

			0.7240

			0.1078

			0.8577

      0.00611

	  0.7290

			0.1203

			0.8885

      0.00451

		

    

			MetaHeac

			0.7263

			0.1077

			0.8615

      0.00606

	  0.7299

			0.1203

			0.8883

      0.00450

		

	



	

		

      Methods

			AliExpress (French, FR)

			AliExpress (America, US)

		

		

			CTR

      CTCVR

	  CTR

      CTCVR

		

		

			AUC

			Logloss

			AUC

      Logloss

	  AUC

			Logloss

			AUC

      Logloss

		

	

	

		

			SingleTask

			0.7259

			0.1002

			0.8737

      0.00435

	  0.7061

			0.1004

			0.8637

      0.00381

		

    

			Shared-Bottom

			0.7245

			0.1004

			0.8700

      0.00439

	  0.7029

			0.1008

			0.8698

      0.00381

		

    

			OMoE

			0.7257

			0.1006

			0.8781

      0.00432

	  0.7049

			0.1007

			0.8701

      0.00381

		

    

			MMoE

			0.7216

			0.1010

			0.8811

      0.00431

	  0.7043

			0.1006

			0.8758

      0.00377

		

    

			PLE

			0.7276

			0.1014

			0.8805

      0.00451

			0.7138

			0.0992

			0.8675

      0.00403

		

    

			AITM

			0.7236

			0.1005

			0.8763

      0.00431

	  0.7048

			0.1004

			0.8730

      0.00377

		

    

			MetaHeac

			0.7249

			0.1005

			0.8813

      0.00429

	  0.7089

			0.1001

			0.8743

      0.00378

		

	



## File Structure



```

.

├── main.py

├── README.md

├── models

│   ├── layers.py

│   ├── aitm.py

│   ├── omoe.py

│   ├── mmoe.py

│   ├── metaheac.py

│   ├── ple.py

│   ├── singletask.py

│   └── sharedbottom.py

└── data

    ├── preprocess.py         # Preprocess the original data

    ├── AliExpress_NL         # AliExpressDataset from Netherlands

    	├── train.csv

	└── test.py

    ├── AliExpress_ES         # AliExpressDataset from Spain

    ├── AliExpress_FR         # AliExpressDataset from French

    └── AliExpress_US         # AliExpressDataset from America

```



## Contact

If you have any problem about this library, please create an issue or send us an Email at:

* [email protected]



## Reference

If you use this repository, please cite the following papers:



```

@inproceedings{zhu2021learning,

  title={Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising},

  author={Zhu, Yongchun and Liu, Yudan and Xie, Ruobing and Zhuang, Fuzhen and Hao, Xiaobo and Ge, Kaikai and Zhang, Xu and Lin, Leyu and Cao, Juan},

  booktitle={Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \& Data Mining},

  pages={4005--4013},

  year={2021}

}

```



```

@inproceedings{xi2021modeling,

  title={Modeling the sequential dependence among audience multi-step conversions with multi-task learning in targeted display advertising},

  author={Xi, Dongbo and Chen, Zhen and Yan, Peng and Zhang, Yinger and Zhu, Yongchun and Zhuang, Fuzhen and Chen, Yu},

  booktitle={Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \& Data Mining},

  pages={3745--3755},

  year={2021}

}

```



Some model implementations and util functions refers to these nice repositories.



- [pytorch-fm](https://github.com/rixwew/pytorch-fm): This package provides a PyTorch implementation of factorization machine models and common datasets in CTR prediction. 

- [MetaHeac](https://github.com/easezyc/MetaHeac): This is an official implementation for Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising.