Skip to content

QunBB/RecSys

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

33 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

RecSys

This project is about recommendation system including rank&match models and metrics which are all implemented by tensorflow 2.x.

You can use these models with model.fit() ,and model.predict() through tf.keras.Model.

The implement for tensorflow 1.x is in this github.

πŸ› οΈ Installation

  • Install via pip

To install, simply use pip to pull down from PyPI.

pip install deep-rec-kit
  • Install from source

If you want to use latest features, or develop new features, you can also build it from source.

git clone https://github.com/QunBB/RecSys
cd RecSys
pip install -e .

πŸ“– Models List

...... means that it will be continuously updated.

Multi-Task Multi-Domain

model paper blog implemented
......
STEM [KDD 2024] Ads Recommendation in a Collapsed and Entangled World zhihu βœ…
PEPNet [KDD 2023] PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information zhihu βœ…
M2M [CIKM 2022] Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling zhihu βœ…
SAR-Net [CIKM 2021] SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios zhihu
Star [CIKM 2021] One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction zhihu βœ…
PLE [RecSys 2020] Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations zhihu βœ…
MMoE [KDD 2018] Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts zhihu βœ…

Rank

model paper blog implemented
......
AdaF^2M^2 [DASFAA 2025] AdaF^2M^2: Comprehensive Learning and Responsive Leveraging Features in Recommendation System zhihu βœ…
HMoE [KDD 2024] Ads Recommendation in a Collapsed and Entangled World zhihu βœ…
GwPFM [KDD 2024] Ads Recommendation in a Collapsed and Entangled World zhihu βœ…
TIN [WWW 2024] Temporal Interest Network for User Response Prediction zhihu βœ…
FiBiNet++ [CIKM 2023 ] FiBiNet++: Reducing Model Size by Low Rank Feature Interaction Layer for CTR Prediction zhihu βœ…
MaskNet [DLP-KDD 2021] MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask zhihu
ContextNet [arXiv 2021] ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding zhihu
DCN V2 [WWW 2021] DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems zhihu βœ…
FEFM [arXiv 2020] Field-Embedded Factorization Machines for Click-through rate prediction zhihu
FiBiNET [RecSys 2019] FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction zhihu βœ…
DSIN [IJCAI 2019] Deep Session Interest Network for Click-Through Rate Prediction zhihu
DIEN [AAAI 2019] Deep Interest Evolution Network for Click-Through Rate Prediction zhihu
DIN [KDD 2018] Deep Interest Network for Click-Through Rate Prediction zhihu βœ…
xDeepFM [KDD 2018] xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems zhihu
FwFM [WWW 2018] Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising zhihu
NFM [SIGIR 2017] Neural Factorization Machines for Sparse Predictive Analytics zhihu
DeepFM [IJCAI 2017] DeepFM: A Factorization-Machine based Neural Network for CTR Prediction zhihu βœ…
Wide & Deep [DLRS 2016] Wide & Deep Learning for Recommender Systems zhihu
Deep Crossing [KDD 2016] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features zhihu
PNN [ICDM 2016] Product-based Neural Networks for User Response Prediction zhihu βœ…
FNN [arXiv 2016] Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction zhihu
FFM [RecSys 2016] Field-aware Factorization Machines for CTR Prediction zhihu

Match

model paper blog implemented
......
Dual Augmented Two-tower Model [DLP-KDD 2021] A Dual Augmented Two-tower Model for Online Large-scale Recommendation zhihu
ComiRec [KDD 2020] Controllable Multi-Interest Framework for Recommendation zhihu
MIND [CIKM 2019] Multi-Interest Network with Dynamic Routing for Recommendation at Tmall zhihu
Youtube DNN [RecSys 2016] Deep Neural Networks for YouTube Recommendations zhihu

πŸ—οΈ Metrics

Metrics for recommendation system.

It will be coming soon.

πŸ“˜ Example

import numpy as np
import tensorflow as tf

from recsys.feature import Field, Task
from recsys.multidomain.pepnet import pepnet

task_list = [
    Task(name='click'),
    Task(name='like'),
    Task(name='fav')
]

num_domain = 3


def create_model():
    fields = [
            Field('uid', vocabulary_size=100),
            Field('item_id', vocabulary_size=20, belong='item'),
            Field('his_item_id', vocabulary_size=20, emb='item_id', length=20, belong='history'),
            Field('context_id', vocabulary_size=20, belong='context'),
            # domain's fields
            Field(f'domain_id', vocabulary_size=num_domain, belong='domain'),
            Field(f'domain_impression', vocabulary_size=1, belong='domain', dtype="float32")
        ]

    model = pepnet(fields, task_list, [64, 32],
                   history_agg='attention', agg_kwargs={}
                   # history_agg='transformer', agg_kwargs={'num_layers': 1, 'd_model': 4, 'num_heads': 2, 'dff': 64}
                   )

    print(model.summary())

    return model


def create_dataset():
    n_samples = 2000
    np.random.seed(2024)
    data = {
        'uid': np.random.randint(0, 100, [n_samples]),
        'item_id': np.random.randint(0, 20, [n_samples]),
        'his_item_id': np.random.randint(0, 20, [n_samples, 20]),
        'context_id': np.random.randint(0, 20, [n_samples]),
        'domain_id': np.random.randint(0, num_domain, [n_samples]),
        'domain_impression': np.random.random([n_samples])
    }
    labels = {t.name: np.random.randint(0, 2, [n_samples]) for t in task_list}

    return data, labels


if __name__ == '__main__':
    model = create_model()
    data, labels = create_dataset()

    model.compile(optimizer='adam', loss=tf.keras.losses.BinaryCrossentropy(), metrics=['accuracy'])
    model.fit(data, labels, batch_size=32, epochs=10)

πŸš€ Mulitple Optimizers

Those layers with prefix "dnn" will use the adam optimizer, and adagrad for prefix "embedding". Also, you must have the default optimizer for legacy layers.

import tensorflow as tf

from recsys.feature import Field, Task
from recsys.multidomain.pepnet import pepnet

task_list = [
    Task(name='click'),
    Task(name='like'),
    Task(name='fav')
]

num_domain = 3


def create_model():
    # absolutely same as the above ......


def create_dataset():
    # absolutely same as the above ......


def train(data, labels):
    model = create_model()

    model.compile(optimizer={'dnn': 'adam', 'embedding': 'Adagrad', 'default': 'adam'},
                  loss=tf.keras.losses.BinaryCrossentropy(),
                  metrics=['accuracy'])
    model.fit(data, labels, batch_size=32, epochs=10)

    checkpoint = tf.train.Checkpoint(model=model)
    checkpoint.save('./pepnet-saved/model.ckpt')

    print(model({k: v[:10] for k, v in data.items()}))

    print(model.optimizer['embedding'].variables())


def restore(data):
    model = create_model()

    model.compile(optimizer={'dnn': 'adam', 'embedding': 'Adagrad', 'default': 'adam'},
                  loss=tf.keras.losses.BinaryCrossentropy(),
                  metrics=['accuracy'])

    checkpoint = tf.train.Checkpoint(model=model)
    checkpoint.restore('./pepnet-saved/model.ckpt-1')

    print(model({k: v[:10] for k, v in data.items()}))

    for layer in model.optimizer:
        model.optimizer[layer].build(model.special_layer_variables[layer])
    print(model.optimizer['embedding'].variables())


if __name__ == '__main__':
    data, labels = create_dataset()

    train(data, labels)

    restore(data)

About

This project is about recommendation system including rank&match models and metrics which are all implemented by `tensorflow 2.x`.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages