{"id":19022599,"url":"https://github.com/uliontse/mlgb","last_synced_at":"2025-05-15T02:08:25.805Z","repository":{"id":215139174,"uuid":"738225898","full_name":"UlionTse/mlgb","owner":"UlionTse","description":"MLGB is a library that includes many models of CTR Prediction \u0026 Recommender System by TensorFlow \u0026 PyTorch. 「妙计包」是一个包含50+点击率预估和推荐系统深度模型的、通过TensorFlow和PyTorch撰写的库。","archived":false,"fork":false,"pushed_at":"2025-03-02T02:41:11.000Z","size":561,"stargazers_count":689,"open_issues_count":0,"forks_count":22,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-05-12T12:07:18.944Z","etag":null,"topics":["autoint","ctr-prediction","dcn","deep-learning","deepfm","din","dsin","dssm","edcn","esmm","fibinet","machine-learning","masknet","mind","mmoe","pepnet","ple","pnn","recommender-system","xdeepfm"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/UlionTse.png","metadata":{"files":{"readme":"README.md","changelog":"change_log.txt","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-01-02T18:18:10.000Z","updated_at":"2025-05-05T07:35:53.000Z","dependencies_parsed_at":"2024-01-05T19:27:20.503Z","dependency_job_id":"d7eaec08-a392-4dae-a0ed-b9515b9875eb","html_url":"https://github.com/UlionTse/mlgb","commit_stats":null,"previous_names":["uliontse/mlgb"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UlionTse%2Fmlgb","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UlionTse%2Fmlgb/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UlionTse%2Fmlgb/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UlionTse%2Fmlgb/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UlionTse","download_url":"https://codeload.github.com/UlionTse/mlgb/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253736107,"owners_count":21955783,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["autoint","ctr-prediction","dcn","deep-learning","deepfm","din","dsin","dssm","edcn","esmm","fibinet","machine-learning","masknet","mind","mmoe","pepnet","ple","pnn","recommender-system","xdeepfm"],"created_at":"2024-11-08T20:26:55.072Z","updated_at":"2025-05-15T02:08:20.781Z","avatar_url":"https://github.com/UlionTse.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/UlionTse/mlgb/blob/main/docs/mlgb_logo.png\" width=\"200\"/\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://pypi.org/project/mlgb\"\u003e\u003cimg alt=\"PyPI - Version\" src=\"https://img.shields.io/pypi/v/mlgb.svg?color=blue\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://anaconda.org/conda-forge/mlgb\"\u003e\u003cimg alt=\"Conda - Version\" src=\"https://img.shields.io/conda/vn/conda-forge/mlgb.svg?color=blue\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/mlgb\"\u003e\u003cimg alt=\"PyPI - License\" src=\"https://img.shields.io/pypi/l/mlgb.svg?color=brightgreen\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/mlgb\"\u003e\u003cimg alt=\"PyPI - Python\" src=\"https://img.shields.io/pypi/pyversions/mlgb.svg?color=blue\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/mlgb\"\u003e\u003cimg alt=\"PyPI - Status\" src=\"https://img.shields.io/pypi/status/mlgb.svg?color=brightgreen\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/mlgb\"\u003e\u003cimg alt=\"PyPI - Wheel\" src=\"https://img.shields.io/badge/wheel-yes-brightgreen.svg\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/mlgb\"\u003e\u003cimg alt=\"PyPI - Downloads\" src=\"https://static.pepy.tech/personalized-badge/mlgb?period=total\u0026units=international_system\u0026left_text=downloads\u0026left_color=grey\u0026right_color=blue\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/mlgb\"\u003e\u003cimg alt=\"PyPI - TensorFlow\" src=\"https://img.shields.io/badge/TensorFlow-2.10+-yellow.svg\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/mlgb\"\u003e\u003cimg alt=\"PyPI - PyTorch\" src=\"https://img.shields.io/badge/PyTorch-2.1+-tomato.svg\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n* * *\n\n**MLGB** means **M**achine **L**earning of the **G**reat **B**oss, and is called **「妙计包」**.  \n**MLGB** is a library that includes many models of CTR Prediction \u0026 Recommender System by TensorFlow \u0026 PyTorch.\n\n- [Advantages](#advantages)\n- [Supported Models](#supported-models)\n- [Installation](#installation)\n- [Getting Started](#getting-started)\n- [Code Examples](#code-examples)\n- [Citation](#citation)\n\n## Advantages\n\n- **Easy!** Use `mlgb.get_model(model_name, **kwargs)` to get a complex model.\n- **Fast!** Better performance through better code.\n- **Enjoyable!** 50+ ranking \u0026 matching models to use, 2 languages(TensorFlow \u0026 PyTorch) to deploy.\n\n## Supported Models\n\n| ID  | Model Name    | Paper Link                                                                                                                                                                             | Paper Team                                                                   | Paper Year |\n| --- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- | ---------- |\n| \u003ctr\u003e\u003cth colspan=5 align=\"center\"\u003e:open_file_folder: **Ranking-Model::Normal** :point_down:\u003c/th\u003e\u003c/tr\u003e |\n| 1   | LR            | [Predicting Clicks: Estimating the Click-Through Rate for New Ads](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/predictingclicks.pdf)                           | Microsoft                                                                    | 2007       |\n| 2   | PLM/MLR       | [Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction](https://arxiv.org/pdf/1704.05194.pdf)                                                                | Alibaba                                                                      | 2017       |\n| 3   | MLP/DNN       | [Neural Networks for Pattern Recognition](http://diyhpl.us/~bryan/papers2/ai/ahuman-pdf-only/neural-networks/2005-Pattern%20Recognition.pdf)                                           | Christopher M. Bishop(Microsoft, 1997-Present), Foreword by Geoffrey Hinton. | 1995       |\n| 4   | DLRM          | [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://arxiv.org/pdf/1906.00091.pdf)                                                              | Facebook(Meta)                                                               | 2019       |\n| 5   | MaskNet       | [MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask](https://arxiv.org/pdf/2102.07619.pdf)                                                 | Weibo(Sina)                                                                  | 2021       |\n|     |               |                                                                                                                                                                                        |                                                                              |            |\n| 6   | DCM/DeepCross | [Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features](https://www.kdd.org/kdd2016/papers/files/adf0975-shanA.pdf)                                        | Microsoft                                                                    | 2016       |\n| 7   | DCN           | [DCN V2: Improved Deep \u0026 Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://arxiv.org/pdf/2008.13535.pdf), [v1](https://arxiv.org/pdf/1708.05123.pdf) | Google(Alphabet)                                                             | 2017, 2020 |\n| 8   | EDCN          | [Enhancing Explicit and Implicit Feature Interactions via Information Sharing for Parallel Deep CTR Models](https://dlp-kdd.github.io/assets/pdf/DLP-KDD_2021_paper_12.pdf)            | Huawei                                                                       | 2021       |\n|     |               |                                                                                                                                                                                        |                                                                              |            |\n| 9   | FM            | [Factorization Machines](https://cseweb.ucsd.edu/classes/fa17/cse291-b/reading/Rendle2010FM.pdf)                                                                                       | Steffen Rendle(Google, 2013-Present)                                         | 2010       |\n| 10  | FFM           | [Field-aware Factorization Machines for CTR Prediction](https://www.csie.ntu.edu.tw/~cjlin/papers/ffm.pdf)                                                                             | NTU                                                                          | 2016       |\n| 11  | HOFM          | [Higher-Order Factorization Machines](https://arxiv.org/pdf/1607.07195v2.pdf)                                                                                                          | NTT                                                                          | 2016       |\n| 12  | FwFM          | [Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising](https://arxiv.org/pdf/1806.03514.pdf)                                                 | Junwei Pan(Yahoo), etc.                                                      | 2018, 2020 |\n| 13  | FmFM          | [FM^2: Field-matrixed Factorization Machines for Recommender Systems](https://arxiv.org/pdf/2102.12994v2.pdf)                                                                          | Yahoo                                                                        | 2021       |\n| 14  | FEFM          | [FIELD-EMBEDDED FACTORIZATION MACHINES FOR CLICK-THROUGH RATE PREDICTION](https://arxiv.org/pdf/2009.09931v2.pdf)                                                                      | Harshit Pande(Adobe)                                                         | 2020, 2021 |\n| 15  | AFM           | [Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks](https://arxiv.org/pdf/1708.04617.pdf)                                         | ZJU\u0026NUS(Jun Xiao(ZJU), Xiangnan He(NUS), etc.)                               | 2017       |\n| 16  | LFM           | [Learning Feature Interactions with Lorentzian Factorization Machine](https://arxiv.org/pdf/1911.09821.pdf)                                                                            | EBay                                                                         | 2019       |\n| 17  | IFM           | [An Input-aware Factorization Machine for Sparse Prediction](https://www.ijcai.org/proceedings/2019/0203.pdf)                                                                          | THU                                                                          | 2019       |\n| 18  | DIFM          | [A Dual Input-aware Factorization Machine for CTR Prediction](https://www.ijcai.org/proceedings/2020/0434.pdf)                                                                         | THU                                                                          | 2020       |\n|     |               |                                                                                                                                                                                        |                                                                              |            |\n| 19  | FNN           | [Deep Learning over Multi-field Categorical Data – A Case Study on User Response Prediction](https://arxiv.org/pdf/1601.02376.pdf)                                                     | UCL(Weinan Zhang(UCL, SJTU), etc.)                                           | 2016       |\n| 20  | PNN           | [Product-based Neural Networks for User Response](https://arxiv.org/pdf/1611.00144.pdf)                                                                                                | SJTU\u0026UCL(Yanru Qu(SJTU), Weinan Zhang(SJTU, UCL), etc.)                      | 2016       |\n| 21  | PIN           | [Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data](https://arxiv.org/pdf/1807.00311.pdf)                                                   | Huawei(Yanru Qu(Huawei(2017.3-2018.3), SJTU), Weinan Zhang(SJTU, UCL), etc.) | 2018       |\n| 22  | ONN/NFFM      | [Operation-aware Neural Networks for User Response Prediction](https://arxiv.org/pdf/1904.12579.pdf)                                                                                   | NJU                                                                          | 2019       |\n| 23  | AFN           | [Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions](https://arxiv.org/pdf/1909.03276v2.pdf)                                                                 | SJTU                                                                         | 2019, 2020 |\n|     |               |                                                                                                                                                                                        |                                                                              |            |\n| 24  | NFM           | [Neural Factorization Machines for Sparse Predictive Analytics](https://arxiv.org/pdf/1708.05027.pdf)                                                                                  | NUS(Xiangnan He(NUS))                                                        | 2017       |\n| 25  | WDL           | [Wide \u0026 Deep Learning for Recommender Systems](https://arxiv.org/pdf/1606.07792.pdf)                                                                                                   | Google(Alphabet)                                                             | 2016       |\n| 26  | DeepFM        | [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://arxiv.org/pdf/1703.04247.pdf)                                                                        | Huawei                                                                       | 2017       |\n| 27  | DeepFEFM      | [FIELD-EMBEDDED FACTORIZATION MACHINES FOR CLICK-THROUGH RATE PREDICTION](https://arxiv.org/pdf/2009.09931v2.pdf)                                                                      | Harshit Pande(Adobe)                                                         | 2020, 2021 |\n| 28  | FLEN          | [FLEN: Leveraging Field for Scalable CTR Prediction](https://arxiv.org/pdf/1911.04690v4.pdf)                                                                                           | Meitu                                                                        | 2019, 2020 |\n|     |               |                                                                                                                                                                                        |                                                                              |            |\n| 29  | CCPM          | [A Convolutional Click Prediction Model](http://wnzhang.net/share/rtb-papers/cnn-ctr.pdf)                                                                                              | CASIA                                                                        | 2015       |\n| 30  | FGCNN         | [Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1904.04447.pdf)                                                           | Huawei                                                                       | 2019       |\n| 31  | XDeepFM       | [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://arxiv.org/pdf/1803.05170v3.pdf)                                                        | Microsoft(Jianxun Lian(USTC, Microsoft(2018.7-Present)), etc.)               | 2018       |\n| 32  | FiBiNet       | [FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction](https://arxiv.org/pdf/1905.09433.pdf)                                       | Weibo(Sina)                                                                  | 2019       |\n| 33  | AutoInt       | [AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://arxiv.org/pdf/1810.11921v2.pdf)                                                           | PKU                                                                          | 2018, 2019 |\n| \u003ctr\u003e\u003cth colspan=5 align=\"center\"\u003e:open_file_folder: **Ranking-Model::Sequential** :point_down:\u003c/th\u003e\u003c/tr\u003e |\n| 34  | GRU4Rec       | [Session-based Recommendations with Recurrent Neural Networks](https://arxiv.org/pdf/1511.06939.pdf)                                                                                   | Telefonica                                                                   | 2015, 2016 |\n| 35  | Caser         | [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://arxiv.org/pdf/1809.07426.pdf)                                                              | SFU                                                                          | 2018       |\n| 36  | SASRec        | [Self-Attentive Sequential Recommendation](https://arxiv.org/pdf/1808.09781.pdf)                                                                                                       | UCSD                                                                         | 2018       |\n| 37  | BERT4Rec      | [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://arxiv.org/pdf/1904.06690.pdf)                                                | Alibaba                                                                      | 2019       |\n| 38  | BST           | [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://arxiv.org/pdf/1905.06874.pdf)                                                                         | Alibaba                                                                      | 2019       |\n| 39  | DIN           | [Deep Interest Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1706.06978v4.pdf), [v1](https://arxiv.org/pdf/1706.06978v1.pdf)                                        | Alibaba                                                                      | 2017, 2018 |\n| 40  | DIEN          | [Deep Interest Evolution Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1809.03672.pdf)                                                                              | Alibaba                                                                      | 2018       |\n| 41  | DSIN          | [Deep Session Interest Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1905.06482.pdf)                                                                                | Alibaba                                                                      | 2019       |\n| \u003ctr\u003e\u003cth colspan=5 align=\"center\"\u003e:open_file_folder: **Ranking-Model::Multitask** :point_down:\u003c/th\u003e\u003c/tr\u003e |\n| 42  | SharedBottom  | [An Overview of Multi-Task Learning in Deep Neural Networks](https://arxiv.org/pdf/1706.05098.pdf)                                                                                     | Sebastian Ruder(InsightCentre)                                               | 2017       |\n| 43  | ESMM          | [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://arxiv.org/pdf/1804.07931.pdf)                                                 | Alibaba                                                                      | 2018       |\n| 44  | MMoE          | [Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts](https://dl.acm.org/doi/pdf/10.1145/3219819.3220007)                                            | Google(Alphabet)                                                             | 2018       |\n| 45  | PLE           | [Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations](https://www.sci-hub.se/10.1145/3383313.3412236)                       | Tencent                                                                      | 2020       |\n| 46  | PEPNet        | [PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information](https://arxiv.org/pdf/2302.01115.pdf)                                          | Kuaishou                                                                     | 2023       |\n| \u003ctr\u003e\u003cth colspan=5 align=\"center\"\u003e:open_file_folder: **Matching-Model** :point_down:\u003c/th\u003e\u003c/tr\u003e |\n| 47  | NCF           | [Neural Collaborative Filtering](https://arxiv.org/pdf/1708.05031.pdf)                                                                                                                 | NUS(Xiangnan He(NUS), etc)                                                   | 2017       |\n| 48  | MatchFM       | [Factorization Machines](https://cseweb.ucsd.edu/classes/fa17/cse291-b/reading/Rendle2010FM.pdf)                                                                                       | Steffen Rendle(Google, 2013-Present)                                         | 2010       |\n| 49  | DSSM          | [Learning deep structured semantic models for web search using clickthrough data](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/cikm2013_DSSM_fullversion.pdf)   | Microsoft                                                                    | 2013       |\n| 50  | EBR           | [Embedding-based Retrieval in Facebook Search](https://browse.arxiv.org/pdf/2006.11632.pdf)                                                                                            | Facebook(Meta)                                                               | 2020       |\n| 51  | YoutubeDNN    | [Deep Neural Networks for YouTube Recommendations](https://static.googleusercontent.com/media/research.google.com/zh-CN//pubs/archive/45530.pdf)                                       | Google(Alphabet)                                                             | 2016       |\n| 52  | MIND          | [Multi-Interest Network with Dynamic Routing for Recommendation at Tmall](https://arxiv.org/pdf/1904.08030.pdf)                                                                        | Alibaba                                                                      | 2019       |\n|     |               |                                                                                                                                                                                        |                                                                              |            |\n\n## Installation\n\n```sh\n# PYPI\npip install --upgrade mlgb\n\n# Conda\nconda install conda-forge::mlgb\n```\n\n## Getting Started\n\n```python\nimport mlgb\n\n# parameters of get_model:\nhelp(mlgb.get_model)\n\n\"\"\"\nget_model(feature_names, model_name='LR', task='binary', aim='ranking', lang='TensorFlow', device=None, seed=None, **kwargs)\n    :param feature_names: tuple(tuple(dict)), must. Embedding need vocabulary size and custom embed_dim of features.\n    :param model_name: str, default 'LR'. Union[`mlgb.ranking_models`, `mlgb.matching_models`, `mlgb.mtl_models`]\n    :param task: str, default 'binary'. Union['binary', 'regression', 'multiclass:{int}']\n    :param aim: str, default 'ranking'. Union['ranking', 'matching', 'mtl']\n    :param lang: str, default 'TensorFlow'. Union['TensorFlow', 'PyTorch', 'tf', 'torch']\n    :param device: Optional[str, int], default None. Only for PyTorch.\n    :param seed: Optional[int], default None.\n    :param **kwargs: more model parameters by `mlgb.get_model_help(model_name)`.\n\"\"\"\n\n# parameters of model:\nmlgb.get_model_help(model_name='LR', lang='tf')\n\n\"\"\"\n class LR(tf.keras.src.models.model.Model)\n |  LR(feature_names, task='binary', seed=None, inputs_if_multivalued=False, inputs_if_sequential=False, inputs_if_embed_dense=False, embed_dim=32, embed_2d_dim=None, embed_l2=0.0, embed_initializer=None, pool_mv_mode='Pooling:average', pool_mv_axis=2, pool_mv_l2=0.0, pool_mv_initializer=None, pool_seq_mode='Pooling:average', pool_seq_axis=1, pool_seq_l2=0.0, pool_seq_initializer=None, linear_if_bias=True, linear_l1=0.0, linear_l2=0.0, linear_initializer=None)\n |  \n |  Methods defined here:\n |  \n |  __init__(self, feature_names, task='binary', seed=None, inputs_if_multivalued=False, inputs_if_sequential=False, inputs_if_embed_dense=False, embed_dim=32, embed_2d_dim=None, embed_l2=0.0, embed_initializer=None, pool_mv_mode='Pooling:average', pool_mv_axis=2, pool_mv_l2=0.0, pool_mv_initializer=None, pool_seq_mode='Pooling:average', pool_seq_axis=1, pool_seq_l2=0.0, pool_seq_initializer=None, linear_if_bias=True, linear_l1=0.0, linear_l2=0.0, linear_initializer=None)\n |      Model Name: LR(LinearOrLogisticRegression)\n |      Paper Team: Microsoft\n |      Paper Year: 2007\n |      Paper Name: \u003cPredicting Clicks: Estimating the Click-Through Rate for New Ads\u003e\n |      Paper Link: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/predictingclicks.pdf\n |      \n |      Task Inputs Parameters:\n |          :param feature_names: tuple(tuple(dict)), must. Embedding need vocabulary size and custom embed_dim of features.\n |          :param task: str, default 'binary'. Union['binary', 'regression']\n |          :param seed: Optional[int], default None.\n |          :param inputs_if_multivalued: bool, default False.\n |          :param inputs_if_sequential: bool, default False.\n |          :param inputs_if_embed_dense: bool, default False.\n |          :param embed_dim: int, default 32.\n |          :param embed_2d_dim: Optional[int], default None. When None, each field has own embed_dim by feature_names.\n |          :param embed_l2: float, default 0.0.\n |          :param embed_initializer: Optional[str], default None. When None, activation judge first, xavier_normal end.\n |          :param pool_mv_mode: str, default 'Pooling:average'. Pooling mode of multivalued inputs. Union[\n |                              'Attention', 'Weighted', 'Pooling:max', 'Pooling:average', 'Pooling:sum']\n |          :param pool_mv_axis: int, default 2. Pooling axis of multivalued inputs.\n |          :param pool_mv_l2: float, default 0.0. When pool_mv_mode is in ('Weighted', 'Attention'), it works.\n |          :param pool_mv_initializer: Optional[str], default None. When None, activation judge first,\n |                              xavier_normal end. When pool_mv_mode is in ('Weighted', 'Attention'), it works.\n |          :param pool_seq_mode: str, default 'Pooling:average'. Pooling mode of sequential inputs. Union[\n |                              'Attention', 'Weighted', 'Pooling:max', 'Pooling:average', 'Pooling:sum']\n |          :param pool_seq_axis: int, default 1. Pooling axis of sequential inputs.\n |          :param pool_seq_l2: float, default 0.0. When pool_seq_mode is in ('Weighted', 'Attention'), it works.\n |          :param pool_seq_initializer: Optional[str], default None. When None, activation judge first,\n |                              xavier_normal end. When pool_seq_mode is in ('Weighted', 'Attention'), it works.\n |      \n |      Task Model Parameters:\n |          :param linear_if_bias: bool, default True.\n |          :param linear_l1: float, default 0.0.\n |          :param linear_l2: float, default 0.0.\n |          :param linear_initializer: Optional[str], default None. When None, activation judge first, xavier_normal end.\n\"\"\"\n```\n\n## Code Examples\n\n| Code Examples                                                          |\n| ---------------------------------------------------------------------- |\n| [TensorFlow](https://github.com/UlionTse/mlgb/tree/main/mlgb/examples) |\n| [PyTorch](https://github.com/UlionTse/mlgb/tree/main/mlgb/examples)    |\n\n## Citation\n\nIf you use this for research, please cite it using the following BibTeX entry. Thanks.\n\n```bibtex\n@misc{uliontse2020mlgb,\n  author = {UlionTse},\n  title = {MLGB is a library that includes many models of CTR Prediction \u0026 Recommender System by TensorFlow \u0026 PyTorch},\n  year = {2020},\n  publisher = {GitHub},\n  journal = {GitHub Repository},\n  howpublished = {\\url{https://github.com/UlionTse/mlgb}},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fuliontse%2Fmlgb","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fuliontse%2Fmlgb","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fuliontse%2Fmlgb/lists"}