fuxictr 1.0.1

A configurable, tunable, and reproducible library for CTR prediction

FuxiCTR

Click-through rate (CTR) prediction is an critical task for many industrial applications such as online advertising, recommender systems, and sponsored search. FuxiCTR provides an open-source library for CTR prediction, with stunning features in configurability, tunability, and reproducibility. It also supports the development of Open-CTR-Benchmark, making open benchmarking for CTR prediction available.

Model List

Publication	Model	Paper	Available
WWW'07	LR	Predicting Clicks: Estimating the Click-Through Rate for New Ads	:heavy_check_mark:
ICDM'10	FM	Factorization Machines	:heavy_check_mark:
CIKM'15	CCPM	A Convolutional Click Prediction Model	:heavy_check_mark:
RecSys'16	FFM	Field-aware Factorization Machines for CTR Prediction	:heavy_check_mark:
RecSys'16	YoutubeDNN	Deep Neural Networks for YouTube Recommendations	:heavy_check_mark:
DLRS'16	Wide&Deep	Wide & Deep Learning for Recommender Systems	:heavy_check_mark:
ECIR'16	FNN	Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction	:heavy_check_mark:
ICDM'16	IPNN	Product-based Neural Networks for User Response Prediction	:heavy_check_mark:
KDD'16	DeepCross	Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features	:heavy_check_mark:
NIPS'16	HOFM	Higher-Order Factorization Machines	:heavy_check_mark:
IJCAI'17	DeepFM	DeepFM: A Factorization-Machine based Neural Network for CTR Prediction	:heavy_check_mark:
SIGIR'17	NFM	Neural Factorization Machines for Sparse Predictive Analytics	:heavy_check_mark:
IJCAI'17	AFM	Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks	:heavy_check_mark:
ADKDD'17	DCN	Deep & Cross Network for Ad Click Predictions	:heavy_check_mark:
WWW'18	FwFM	Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising	:heavy_check_mark:
KDD'18	xDeepFM	xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems	:heavy_check_mark:
KDD'18	DIN	Deep Interest Network for Click-Through Rate Prediction	:heavy_check_mark:
CIKM'19	FiGNN	FiGNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction	:heavy_check_mark:
CIKM'19	AutoInt+	AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks	:heavy_check_mark:
RecSys'19	FiBiNET	FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction	:heavy_check_mark:
WWW'19	FGCNN	Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction	:heavy_check_mark:
AAAI'19	HFM+	Holographic Factorization Machines for Recommendation	:heavy_check_mark:
Neural Networks'20	ONN	Operation-aware Neural Networks for User Response Prediction	:heavy_check_mark:
AAAI'20	AFN+	Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions	:heavy_check_mark:
AAAI'20	LorentzFM	Learning Feature Interactions with Lorentzian Factorization	:heavy_check_mark:
WSDM'20	InterHAt	Interpretable Click-through Rate Prediction through Hierarchical Attention	:heavy_check_mark:
DLP-KDD'20	FLEN	FLEN: Leveraging Field for Scalable CTR Prediction	:heavy_check_mark:

Get Started

1. Run the demo

Please follow the examples in the demo directory to get started. The code workflow is structured as follows:

# Set the data config and model config
feature_cols = [{...}] # define feature columns
label_col = {...} # define label column
params = {...} # set data params and model params

# Set the feature encoding specs
feature_encoder = FeatureEncoder(feature_cols, label_col, ...) # define the feature encoder
feature_encoder.fit(...) # fit and transfrom the data

# Load data generators
train_gen, valid_gen, test_gen = data_generator(feature_encoder, ...)

# Define a model
model = DeepFM(...)

# Train the model
model.fit_generator(train_gen, validation_data=valid_gen, ...)

# Evaluation
model.evaluate_generator(test_gen)

2. Run the benchmark with given experiment_ID

For reproducing the experiment result, you can run the benchmarking script with the corresponding config file as follows.

• --config: The config directory of data and model config files.
• --expid: The specific experiment_ID that records the detailed data and model settings.
• --gpu: The gpu index used for experiment, and -1 for CPU.

For example, DeepFM_test is an expid located in config/model_config/tests.yaml.

cd benchmarks
python run.py --config ../config --expid DeepFM_test --gpu 0

3. Tune the model hyper-parameters

For model hyper-parameters tuning, you can apply grid-search over the specified tuning space with the following script.

• --config: The config file that defines the tuning space
• --gpu: The available gpus for parameters tuning.

cd benchmarks
python run_param_tuner.py --config ./FM_criteo_x4_001/FM_criteo_x4_tuner_config_01.yaml --gpu 0

Code Structure

Check an overview of code structure for more details on API design.

Dependency

FuxiCTR has the following requirements to install.

• python 3.6.x
• pytorch 1.0.x
• pandas
• numpy
• h5py
• pyyaml

License

The MIT License