Group-Buying Recommendation for Social E-Commerce

Overview

Group-Buying Recommendation for Social E-Commerce

This is the official implementation of the paper Group-Buying Recommendation for Social E-Commerce (PDF) accepted by ICDE'2021.

Group-Buying Dataset

Group buying, as an emerging form of purchase in social e-commerce websites, such as Pinduoduo.com , has recently achieved great success. In this new business model, users, initiator, can launch a group and share products to their social networks, and when there are enough friends, participants, join it, the deal is clinched. Group-buying recommendation for social ecommerce, which recommends an item list when users want to launch a group, plays an important role in the group success ratio and sales.

The information about the dataset can be found in BeiBei/readme.txt.

Code

We separate model definition from the framework librecframework for easily understanding.

You can find the framework librecframework in https://github.com/Sweetnow/librecframework.

Both modules mentioned in requirements.txt and librecframework should be installed before running the code.

More details about our codes will be added soon.

Usage

  1. Download both librecframework and this repo
git clone [email protected]:Sweetnow/librecframework.git
git clone [email protected]:Sweetnow/group-buying-recommendation.git
  1. Install librecframework (Python >= 3.8)
cd librecframework/
bash install.sh
  1. Install dgl

  2. Download negative.zip from Release, unzip it and copy *.negative.txt to datasets/BeiBei/

wget https://github.com/Sweetnow/group-buying-recommendation/releases/download/v1.0/negative.zip
unzip negative.zip
cp negative/* ${PATH-TO-GROUP-BUYING-RECOMMENDATION}/datasets/BeiBei

PS: negative sampling file is used for testing. More details can be found in Datasets README

  1. Set config/config.json and config/pretrain.json following Docs.

  2. Run the following command to know the CLI and check python environment:

python3 GBGCN train -h
# or
# python3 GBGCN test -h

PS: If you set hyperparameters that support multi input to multi values, the framework will automatically do grid-search accroding to your input. That is, use the Cartesian product of the hyperparameters for training and testing. For example, set --lr 0.1 0.01 -L 1 2, the codes will train and test model with hyperparameters [(0.1, 1), (0.1, 2), (0.01, 1), (0.01, 2)].

Citation

If you want to use our codes or dataset in your research, please cite:

@inproceedings{zhang2021group,
  title={Group-Buying Recommendation for Social E-Commerce},
  author={Zhang, Jun and Gao, Chen and Jin, Depeng and Li, Yong},
  booktitle={2021 IEEE 37th International Conference on Data Engineering (ICDE)},
  year={2021},
  organization={IEEE}
}

Acknowledgement

Comments
  • About Testing

    About Testing

    Hi,

    Since I always fail to run the testing mode (for both GBMF and GBGCN) due to lack of "model.json", I'm wondering how to save a pretrained (GBMF) model as a json file and how to run the testing mode. Thanks.

    opened by vincenttsai2015 16
  • About negative samples for testing

    About negative samples for testing

    Hi,

    After resolving the issues of testing execution, I'm wondering if the following error is due to the lack of test.negative.txt.

    image

    If so, how can I generate negative samples? Thanks.

    opened by vincenttsai2015 14
  • It was killed before the training process started when the code was reproduced

    It was killed before the training process started when the code was reproduced

    hello,I want to know what the computer configuration should be to successfully reproduce these jobs. I can't reproduce it on 2080ti with 11gb of memory, and it's useless when I try to make the batchsize small enough. Or can you specify the hyperparameter setting?

    opened by ZQSong1997 6
  • Implementing the GBGCN in google colab

    Implementing the GBGCN in google colab

    Hi, After installing setup.py file from the mentioned frame work in the GitHub, I tried to run the GBGCN.py file by this command in Google Colab, "! python GBGCN.py train --tag 'true' --SL2 0.001 --L2 0.001 --lr 1e-2 --layer 2 --alpha 0.6 --beta 0.01 ". The below Errors showed: ( Any help to solve these errors and run the file properly would be appreciated! Just to mentioned that when I tried to run the whole data on GBGCN.py, it was not successful. I think the not enough RAM on colab was the problem( my colab RAM is around 12 GB) so I tried to reduce the size of BeiBei data set( 0.01 of the data set) to tackle this issue. Then these errors showed)

    INFO:root:Environment Arguments(OrderedDict([('dataset', 'BeiBei'), ('device', [0]), ('sample_epoch', 500), ('sample_worker', 16), ('epoch', 500), ('tag', 'true')])) INFO:root:Dataloader Arguments(OrderedDict([('batch_size', 4096), ('batch_worker', 2), ('test_batch_size', 128), ('test_batch_worker', 2)])) INFO:root:Hyperparameter Arguments(OrderedDict([('embedding_size', 32), ('act', 'sigmoid'), ('pretrain', True), ('SL2', [0.001]), ('L2', [0.001]), ('lr', [0.01]), ('layer', [2]), ('alpha', [0.6]), ('beta', [0.01])])) INFO:root:{'comment': '固定参数', 'user': 'user', 'visdom': {'server': '127.0.0.1', 'port': {'BeiBei_itemrec': 16670, 'BeiBei_grouprec': 16670, 'BeiBei_SIGR': 16670, 'BeiBei': 16670, 'comment': '16671 is temporary'}}, 'training': {'test_interval': 5, 'early_stop': 50, 'overfit': {'protected_epoch': 10, 'threshold': 1}}, 'dataset': {'path': './BeiBei', 'seed': 123, 'use_backup': True}, 'logger': {'path': './log', 'policy': 'best'}, 'metric': {'target': {'type': 'NDCG', 'topk': 10}, 'metrics': [{'type': 'Recall', 'topk': 3}, {'type': 'Recall', 'topk': 5}, {'type': 'Recall', 'topk': 10}, {'type': 'Recall', 'topk': 20}, {'type': 'NDCG', 'topk': 3}, {'type': 'NDCG', 'topk': 5}, {'type': 'NDCG', 'topk': 10}, {'type': 'NDCG', 'topk': 20}]}} INFO:root:{'BeiBei': {'GBMF': ''}} DEBUG:root:Load BeiBei/BeiBei/BeiBei-neg-500-123-default.pkl DEBUG:root:finish loading neg sample INFO:root:GPU search space: [0] INFO:root:Auto select GPU 0 WARNING:visdom:Setting up a new session... Exception in user code:

    Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/urllib3/connection.py", line 159, in _new_conn (self._dns_host, self.port), self.timeout, **extra_kw) File "/usr/local/lib/python3.7/dist-packages/urllib3/util/connection.py", line 80, in create_connection raise err File "/usr/local/lib/python3.7/dist-packages/urllib3/util/connection.py", line 70, in create_connection sock.connect(sa) ConnectionRefusedError: [Errno 111] Connection refused

    During handling of the above exception, another exception occurred:

    Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/urllib3/connectionpool.py", line 600, in urlopen chunked=chunked) File "/usr/local/lib/python3.7/dist-packages/urllib3/connectionpool.py", line 354, in _make_request conn.request(method, url, **httplib_request_kw) File "/usr/lib/python3.7/http/client.py", line 1277, in request self._send_request(method, url, body, headers, encode_chunked) File "/usr/lib/python3.7/http/client.py", line 1323, in _send_request self.endheaders(body, encode_chunked=encode_chunked) File "/usr/lib/python3.7/http/client.py", line 1272, in endheaders self._send_output(message_body, encode_chunked=encode_chunked) File "/usr/lib/python3.7/http/client.py", line 1032, in _send_output self.send(msg) File "/usr/lib/python3.7/http/client.py", line 972, in send self.connect() File "/usr/local/lib/python3.7/dist-packages/urllib3/connection.py", line 181, in connect conn = self._new_conn() File "/usr/local/lib/python3.7/dist-packages/urllib3/connection.py", line 168, in _new_conn self, "Failed to establish a new connection: %s" % e) urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPConnection object at 0x7fd8435d5c50>: Failed to establish a new connection: [Errno 111] Connection refused

    During handling of the above exception, another exception occurred:

    Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/requests/adapters.py", line 449, in send timeout=timeout File "/usr/local/lib/python3.7/dist-packages/urllib3/connectionpool.py", line 638, in urlopen _stacktrace=sys.exc_info()[2]) File "/usr/local/lib/python3.7/dist-packages/urllib3/util/retry.py", line 399, in increment raise MaxRetryError(_pool, url, error or ResponseError(cause)) urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host='127.0.0.1', port=16670): Max retries exceeded with url: /env/GBGCN_true-32-0.01-0.001-0.001-2-0.6-0.01-sigmoid-True-True (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fd8435d5c50>: Failed to establish a new connection: [Errno 111] Connection refused'))

    During handling of the above exception, another exception occurred:

    Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/visdom/init.py", line 711, in _send data=json.dumps(msg), File "/usr/local/lib/python3.7/dist-packages/visdom/init.py", line 677, in _handle_post r = self.session.post(url, data=data) File "/usr/local/lib/python3.7/dist-packages/requests/sessions.py", line 578, in post return self.request('POST', url, data=data, json=json, **kwargs) File "/usr/local/lib/python3.7/dist-packages/requests/sessions.py", line 530, in request resp = self.send(prep, **send_kwargs) File "/usr/local/lib/python3.7/dist-packages/requests/sessions.py", line 643, in send r = adapter.send(request, **kwargs) File "/usr/local/lib/python3.7/dist-packages/requests/adapters.py", line 516, in send raise ConnectionError(e, request=request) requests.exceptions.ConnectionError: HTTPConnectionPool(host='127.0.0.1', port=16670): Max retries exceeded with url: /env/GBGCN_true-32-0.01-0.001-0.001-2-0.6-0.01-sigmoid-True-True (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fd8435d5c50>: Failed to establish a new connection: [Errno 111] Connection refused')) INFO:visdom:Socket refused connection, running socketless ERROR:visdom:[Errno 111] Connection refused ERROR:websocket:error from callback <function Visdom.setup_socket..on_close at 0x7fd84346ec20>: on_close() takes 1 positional argument but 3 were given File "/usr/local/lib/python3.7/dist-packages/websocket/_app.py", line 407, in _callback callback(self, *args) Traceback (most recent call last): File "GBGCN.py", line 556, in torch.optim.SGD) File "/usr/local/lib/python3.7/dist-packages/librecframework-1.3.0-py3.7.egg/librecframework/pipeline.py", line 633, in during_running model_class, other_args, trainhooks, optim_type) File "/usr/local/lib/python3.7/dist-packages/librecframework-1.3.0-py3.7.egg/librecframework/pipeline.py", line 239, in during_running model.load_pretrain(self._pretrain[self._eam['dataset']]) File "GBGCN.py", line 102, in load_pretrain pretrain = torch.load(path, map_location='cpu') File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 381, in load f = open(f, 'rb') FileNotFoundError: [Errno 2] No such file or directory: ''

    opened by Ali-khn 5
  • About ranking metric evaluation

    About ranking metric evaluation

    Hi,

    I'm wondering if it is possible to evaluate the ranking metrics of MAP(mean average precision) @ K and HR(hit ratio) @ K of GBMF/GBGCN under librecframework. If yes, how can I modify the code? Thanks.

    opened by vincenttsai2015 2
  • 您好,我在复现您的代码时遇到以下问题,想请教一下。

    您好,我在复现您的代码时遇到以下问题,想请教一下。

    命令: python GBGCN.py train [-h] 错误: Using backend: pytorch usage: GBGCN.py train [-h] [-DS DATASET] [-D DEVICE [DEVICE ...]] -T TAG [-SEP SAMPLE_EPOCH] [-SW SAMPLE_WORKER] [-EP EPOCH] [-BS BATCH_SIZE] [-BW BATCH_WORKER] [-TBS TEST_BATCH_SIZE] [-TBW TEST_BATCH_WORKER] [-EB EMBEDDING_SIZE] [--lr LR [LR ...]] --L2 L2 [L2 ...] --SL2 SL2 [SL2 ...] -L LAYER [LAYER ...] -A ALPHA [ALPHA ...] -B BETA [BETA ...] [--act ACT] [--pretrain | --no-pretrain] GBGCN.py train: error: the following arguments are required: -T/--tag, --L2, --SL2, -L/--layer, -A/--alpha, -B/--beta

    opened by Ganoder 2
  • Negative sample files

    Negative sample files

    Hi, My question is how to use negative sample file in order to run the whole model correctly? should I copy the file in BeiBei folder? Can I run the model correctly without "negative sample file"? Any instruction from scratch would be of any help. Thanks

    opened by Ali-khn 2
  • TypeError: metaclass conflict: the metaclass of a derived class must be a (non-strict) subclass of the metaclasses of all its bases

    TypeError: metaclass conflict: the metaclass of a derived class must be a (non-strict) subclass of the metaclasses of all its bases

    作者您好,我安装了requirements.txt和librecframework之后运行GBGCN.py,遇到了以下错误: Traceback (most recent call last): File "GBGCN.py", line 14, in from librecframework.argument.manager import HyperparamManager File "C:\Users\ZSX\AppData\Roaming\Python\Python36\site-packages\librecframework\argument_init_.py", line 11, in class Argument(NamedTuple, Generic[T]): TypeError: metaclass conflict: the metaclass of a derived class must be a (non-strict) subclass of the metaclasses of all its bases

    请问这是什么情况呢

    opened by zanshuxun 2
Owner
Jun Zhang
EE, Tsinghua University
Jun Zhang
Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction

MGNN-SPred This is our Tensorflow implementation for the paper: WenWang,Wei Zhang, Shukai Liu, Qi Liu, Bo Zhang, Leyu Lin, and Hongyuan Zha. 2020. Bey

Wen Wang 18 Jan 02, 2023
ToR[e]cSys is a PyTorch Framework to implement recommendation system algorithms

ToR[e]cSys is a PyTorch Framework to implement recommendation system algorithms, including but not limited to click-through-rate (CTR) prediction, learning-to-ranking (LTR), and Matrix/Tensor Embeddi

LI, Wai Yin 90 Oct 08, 2022
A framework for large scale recommendation algorithms.

A framework for large scale recommendation algorithms.

Alibaba Group - PAI 880 Jan 03, 2023
Codes for AAAI'21 paper 'Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation'

DHCN Codes for AAAI 2021 paper 'Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation'. Please note that the default link

Xin Xia 124 Dec 14, 2022
Self-supervised Graph Learning for Recommendation

SGL This is our Tensorflow implementation for our SIGIR 2021 paper: Jiancan Wu, Xiang Wang, Fuli Feng, Xiangnan He, Liang Chen, Jianxun Lian,and Xing

151 Dec 20, 2022
Accuracy-Diversity Trade-off in Recommender Systems via Graph Convolutions

Accuracy-Diversity Trade-off in Recommender Systems via Graph Convolutions This repository contains the code of the paper "Accuracy-Diversity Trade-of

2 Sep 16, 2022
EXEMPLO DE SISTEMA ESPECIALISTA PARA RECOMENDAR SERIADOS EM PYTHON

exemplo-de-sistema-especialista EXEMPLO DE SISTEMA ESPECIALISTA PARA RECOMENDAR SERIADOS EM PYTHON Resumo O objetivo de auxiliar o usuário na escolha

Josue Lopes 3 Aug 31, 2021
Books Recommendation With Python

Books-Recommendation Business Problem During the last few decades, with the rise

Çağrı Karadeniz 7 Mar 12, 2022
RecList is an open source library providing behavioral, "black-box" testing for recommender systems.

RecList is an open source library providing behavioral, "black-box" testing for recommender systems.

Jacopo Tagliabue 375 Dec 30, 2022
NVIDIA Merlin is an open source library designed to accelerate recommender systems on NVIDIA’s GPUs.

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in

420 Jan 04, 2023
大规模推荐算法库,包含推荐系统经典及最新算法LR、Wide&Deep、DSSM、TDM、MIND、Word2Vec、DeepWalk、SSR、GRU4Rec、Youtube_dnn、NCF、GNN、FM、FFM、DeepFM、DCN、DIN、DIEN、DLRM、MMOE、PLE、ESMM、MAML、xDeepFM、DeepFEFM、NFM、AFM、RALM、Deep Crossing、PNN、BST、AutoInt、FGCNN、FLEN、ListWise等

(中文文档|简体中文|English) 什么是推荐系统? 推荐系统是在互联网信息爆炸式增长的时代背景下,帮助用户高效获得感兴趣信息的关键; 推荐系统也是帮助产品最大限度吸引用户、留存用户、增加用户粘性、提高用户转化率的银弹。 有无数优秀的产品依靠用户可感知的推荐系统建立了良好的口碑,也有无数的公司依

3.6k Dec 30, 2022
Codes for CIKM'21 paper 'Self-Supervised Graph Co-Training for Session-based Recommendation'.

COTREC Codes for CIKM'21 paper 'Self-Supervised Graph Co-Training for Session-based Recommendation'. Requirements: Python 3.7, Pytorch 1.6.0 Best Hype

Xin Xia 43 Jan 04, 2023
Bert4rec for news Recommendation

News-Recommendation-system-using-Bert4Rec-model Bert4rec for news Recommendation

saran pandian 2 Feb 04, 2022
Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

DANSER-WWW-19 This repository holds the codes for Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recom

Qitian Wu 78 Dec 10, 2022
A Python scikit for building and analyzing recommender systems

Overview Surprise is a Python scikit for building and analyzing recommender systems that deal with explicit rating data. Surprise was designed with th

Nicolas Hug 5.7k Jan 01, 2023
[ICDMW 2020] Code and dataset for "DGTN: Dual-channel Graph Transition Network for Session-based Recommendation"

DGTN: Dual-channel Graph Transition Network for Session-based Recommendation This repository contains PyTorch Implementation of ICDMW 2020 (NeuRec @ I

Yujia 25 Nov 17, 2022
A recommendation system for suggesting new books given similar books.

Book Recommendation System A recommendation system for suggesting new books given similar books. Datasets Dataset Kaggle Dataset Notebooks goodreads-E

Sam Partee 2 Jan 06, 2022
E-Commerce recommender demo with real-time data and a graph database

🔍 E-Commerce recommender demo 🔍 This is a simple stream setup that uses Memgraph to ingest real-time data from a simulated online store. Data is str

g-despot 3 Feb 23, 2022
Incorporating User Micro-behaviors and Item Knowledge 59 60 3 into Multi-task Learning for Session-based Recommendation

MKM-SR Incorporating User Micro-behaviors and Item Knowledge into Multi-task Learning for Session-based Recommendation Paper data and code This is the

ciecus 38 Dec 05, 2022
RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems

RecSim NG, a probabilistic platform for multi-agent recommender systems simulation. RecSimNG is a scalable, modular, differentiable simulator implemented in Edward2 and TensorFlow. It offers: a power

Google Research 110 Dec 16, 2022