reczoo/FuxiCTR

---

Click-through rate (CTR) prediction is a critical task for various industrial applications such as online advertising, recommender systems, and sponsored search. FuxiCTR provides an open-source library for CTR prediction, with key features in configurability, tunability, and reproducibility. We hope this project could promote reproducible research and benefit both researchers and practitioners in this field.

Key Features

• Configurable: Both data preprocessing and models are modularized and configurable.

• Tunable: Models can be automatically tuned through easy configurations.

• Reproducible: All the benchmarks can be easily reproduced.

• Extensible: It can be easily extended to any new models, supporting both Pytorch and Tensorflow frameworks.

Model Zoo

No	Publication	Model	Paper	Benchmark	Version
:open_file_folder: Feature Interaction Models
1	WWW'07	LR	Predicting Clicks: Estimating the Click-Through Rate for New Ads :triangular_flag_on_post:Microsoft	:arrow_upper_right:	torch
2	ICDM'10	FM	Factorization Machines	:arrow_upper_right:	torch
3	CIKM'13	DSSM	Learning Deep Structured Semantic Models for Web Search using Clickthrough Data :triangular_flag_on_post:Microsoft	:arrow_upper_right:	torch
4	CIKM'15	CCPM	A Convolutional Click Prediction Model	:arrow_upper_right:	torch
5	RecSys'16	FFM	Field-aware Factorization Machines for CTR Prediction :triangular_flag_on_post:Criteo	:arrow_upper_right:	torch
6	RecSys'16	DNN	Deep Neural Networks for YouTube Recommendations :triangular_flag_on_post:Google	:arrow_upper_right:	torch, tf
7	DLRS'16	Wide&Deep	Wide & Deep Learning for Recommender Systems :triangular_flag_on_post:Google	:arrow_upper_right:	torch, tf
8	ICDM'16	PNN	Product-based Neural Networks for User Response Prediction	:arrow_upper_right:	torch
9	KDD'16	DeepCrossing	Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features :triangular_flag_on_post:Microsoft	:arrow_upper_right:	torch
10	NIPS'16	HOFM	Higher-Order Factorization Machines	:arrow_upper_right:	torch
11	IJCAI'17	DeepFM	DeepFM: A Factorization-Machine based Neural Network for CTR Prediction :triangular_flag_on_post:Huawei	:arrow_upper_right:	torch, tf
12	SIGIR'17	NFM	Neural Factorization Machines for Sparse Predictive Analytics	:arrow_upper_right:	torch
13	IJCAI'17	AFM	Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks	:arrow_upper_right:	torch
14	ADKDD'17	DCN	Deep & Cross Network for Ad Click Predictions :triangular_flag_on_post:Google	:arrow_upper_right:	torch, tf
15	WWW'18	FwFM	Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising :triangular_flag_on_post:Oath, TouchPal, LinkedIn, Alibaba	:arrow_upper_right:	torch
16	KDD'18	xDeepFM	xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems :triangular_flag_on_post:Microsoft	:arrow_upper_right:	torch
17	CIKM'19	FiGNN	FiGNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction	:arrow_upper_right:	torch
18	CIKM'19	AutoInt/AutoInt+	AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks	:arrow_upper_right:	torch
19	RecSys'19	FiBiNET	FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction :triangular_flag_on_post:Sina Weibo	:arrow_upper_right:	torch
20	WWW'19	FGCNN	Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction :triangular_flag_on_post:Huawei	:arrow_upper_right:	torch
21	AAAI'19	HFM/HFM+	Holographic Factorization Machines for Recommendation	:arrow_upper_right:	torch
22	Arxiv'19	DLRM	Deep Learning Recommendation Model for Personalization and Recommendation Systems :triangular_flag_on_post:Facebook	:arrow_upper_right:	torch
23	NeuralNetworks'20	ONN	Operation-aware Neural Networks for User Response Prediction	:arrow_upper_right:	torch, tf
24	AAAI'20	AFN/AFN+	Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions	:arrow_upper_right:	torch
25	AAAI'20	LorentzFM	Learning Feature Interactions with Lorentzian Factorization :triangular_flag_on_post:eBay	:arrow_upper_right:	torch
26	WSDM'20	InterHAt	Interpretable Click-through Rate Prediction through Hierarchical Attention :triangular_flag_on_post:NEC Labs, Google	:arrow_upper_right:	torch
27	DLP-KDD'20	FLEN	FLEN: Leveraging Field for Scalable CTR Prediction :triangular_flag_on_post:Tencent	:arrow_upper_right:	torch
28	CIKM'20	DeepIM	Deep Interaction Machine: A Simple but Effective Model for High-order Feature Interactions :triangular_flag_on_post:Alibaba, RealAI	:arrow_upper_right:	torch
29	WWW'21	FmFM	FM^2: Field-matrixed Factorization Machines for Recommender Systems :triangular_flag_on_post:Yahoo	:arrow_upper_right:	torch
30	WWW'21	DCN-V2	DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems :triangular_flag_on_post:Google	:arrow_upper_right:	torch
31	CIKM'21	DESTINE	Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction :triangular_flag_on_post:Alibaba	:arrow_upper_right:	torch
32	CIKM'21	EDCN	Enhancing Explicit and Implicit Feature Interactions via Information Sharing for Parallel Deep CTR Models :triangular_flag_on_post:Huawei	:arrow_upper_right:	torch
33	DLP-KDD'21	MaskNet	MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask :triangular_flag_on_post:Sina Weibo	:arrow_upper_right:	torch
34	SIGIR'21	SAM	Looking at CTR Prediction Again: Is Attention All You Need? :triangular_flag_on_post:BOSS Zhipin	:arrow_upper_right:	torch
35	KDD'21	AOANet	Architecture and Operation Adaptive Network for Online Recommendations :triangular_flag_on_post:Didi Chuxing	:arrow_upper_right:	torch
36	AAAI'23	FinalMLP	FinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction :triangular_flag_on_post:Huawei	:arrow_upper_right:	torch
37	SIGIR'23	FinalNet	FINAL: Factorized Interaction Layer for CTR Prediction :triangular_flag_on_post:Huawei	:arrow_upper_right:	torch
38	SIGIR'23	EulerNet	EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction :triangular_flag_on_post:Huawei	:arrow_upper_right:	torch
39	CIKM'23	GDCN	Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction :triangular_flag_on_post:Microsoft		torch
40	ICML'24	WuKong	Wukong: Towards a Scaling Law for Large-Scale Recommendation :triangular_flag_on_post:Meta	:arrow_upper_right:	torch
41	KDD'25	QNN-α	Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction :triangular_flag_on_post:Huawei	:arrow_upper_right:	torch
:open_file_folder: Behavior Sequence Modeling
42	KDD'18	DIN	Deep Interest Network for Click-Through Rate Prediction :triangular_flag_on_post:Alibaba	:arrow_upper_right:	torch
43	AAAI'19	DIEN	Deep Interest Evolution Network for Click-Through Rate Prediction :triangular_flag_on_post:Alibaba	:arrow_upper_right:	torch
44	DLP-KDD'19	BST	Behavior Sequence Transformer for E-commerce Recommendation in Alibaba :triangular_flag_on_post:Alibaba	:arrow_upper_right:	torch
45	CIKM'20	DMIN	Deep Multi-Interest Network for Click-through Rate Prediction :triangular_flag_on_post:Alibaba	:arrow_upper_right:	torch
46	AAAI'20	DMR	Deep Match to Rank Model for Personalized Click-Through Rate Prediction :triangular_flag_on_post:Alibaba	:arrow_upper_right:	torch
47	KDD'23	TransAct	TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest :triangular_flag_on_post:Pinterest	:arrow_upper_right:	torch
:open_file_folder: Long Sequence Modeling
48	CIKM'20	SIM	Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction :triangular_flag_on_post:Alibaba		torch
49	DLP-KDD'22	ETA	Efficient Long Sequential User Data Modeling for Click-Through Rate Prediction :triangular_flag_on_post:Alibaba		torch
50	CIKM'22	SDIM	Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction :triangular_flag_on_post:Meituan		torch
51	KDD'23	TWIN	TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou :triangular_flag_on_post:KuaiShou		torch
52	KDD'25	MIRRN	Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction :triangular_flag_on_post:Huawei		torch
:open_file_folder: Dynamic Weight Network
53	NeurIPS'22	APG	APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction :triangular_flag_on_post:Alibaba	:arrow_upper_right:	torch
54	KDD'23	PPNet	PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information :triangular_flag_on_post:KuaiShou	:arrow_upper_right:	torch
:open_file_folder: Multi-Task Modeling
55	Arxiv'17	ShareBottom	An Overview of Multi-Task Learning in Deep Neural Networks		torch
56	KDD'18	MMoE	Modeling Task Relationships in Multi-task Learning with Multi-Gate Mixture-of-Experts :triangular_flag_on_post:Google		torch
57	RecSys'20	PLE	Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations :triangular_flag_on_post:Tencent		torch

Benchmarking

We have benchmarked FuxiCTR models on a set of open datasets as follows:

• :star: Benchmark datasets for CTR prediction
• :star: Benchmark settings and running steps
• :star: Benchmark leaderboard for CTR prediction

Dependencies

The following dependencies are recommended:

• python>=3.10
• pytorch>=2.7.1 (if using for torch models)
• tensorflow>=2.21.0 (if using for tensorflow models)

Please install other required packages via pip install -r requirements.txt.

Quick Start

1. Run the demo examples

   Examples are provided in the demo directory to show some basic usage of FuxiCTR. Users can run the examples for quick start and to understand the workflow.

   cd demo
   python example1_build_dataset_to_parquet.py
   python example2_DeepFM_with_parquet_input.py
   

2. Run a model on tiny data

   Users can easily run each model in the model zoo following the commands below, which is a demo for running DCN. In addition, users can modify the dataset config and model config files to run on their own datasets or with new hyper-parameters. More details can be found in the README.

   cd model_zoo/DCN/DCN_torch
   python run_expid.py --expid DCN_test --gpu 0
   
   # Change `MODEL` according to the target model name
   cd model_zoo/MODEL
   python run_expid.py --expid MODEL_test --gpu 0
   

3. Run a model on benchmark datasets (e.g., Criteo)

   Users can follow the benchmark section to get benchmark datasets and running steps for reproducing the existing results. Please see an example here: https://github.com/reczoo/BARS/tree/main/ranking/ctr/DCNv2/DCNv2_criteo_x1

4. Implement a new model

   The FuxiCTR library is designed to be modularized, so that every component can be overwritten by users according to their needs. In many cases, only the model class needs to be implemented for a new customized model. If data preprocessing or data loader is not directly applicable, one can also overwrite a new one through the core APIs. We show a concrete example which implements our new model FinalMLP that has been recently published in AAAI 2023.

5. Tune hyper-parameters of a model

   FuxiCTR currently support fast grid search of hyper-parameters of a model using multiple GPUs. The following example shows the grid search of 8 experiments with 4 GPUs.

   cd experiment
   python run_param_tuner.py --config config/DCN_tiny_parquet_tuner_config.yaml --gpu 0 1 2 3 0 1 2 3
   

🔥 Citation

If you use our code or benchmarks in your public research, please cite the following two papers.

• Jieming Zhu, Quanyu Dai, Liangcai Su, Rong Ma, Jinyang Liu, Guohao Cai, Xi Xiao, Rui Zhang. BARS: Towards Open Benchmarking for Recommender Systems. The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2022. [Bibtex]
• Jieming Zhu, Jinyang Liu, Shuai Yang, Qi Zhang, Xiuqiang He. BARS-CTR: Open Benchmarking for Click-Through Rate Prediction. The 30th ACM International Conference on Information and Knowledge Management (CIKM), 2021. [Bibtex]

🙋 Contributing

We welcome contributions via issues or pull requests. All contributors are highly appreciated and will be recognized in the contributors list.