alibaba / nann
A flexible, high-performance framework for large-scale retrieval problems based on TensorFlow.
☆150Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for nann
- ☆318Updated 3 weeks ago
- embedx 是基于 c++ 开发的、完全自研的分布式 embedding 训练和推理框架。它目前支持 图模型、深度排序、召回模型和图与排序、图与召回的联合训练模型等☆299Updated 5 months ago
- Distributed LR、 FM model on Parameter Server. FTRL and SGD Optimization Algorithm.☆221Updated 6 years ago
- Large batch training of CTR models based on DeepCTR with CowClip.☆163Updated last year
- A library for end-to-end learning of embedding index and retrieval model☆61Updated 3 years ago
- A high-performance framework for training wide-and-deep recommender systems on heterogeneous cluster☆157Updated 7 months ago
- Advanced Retrieval Algorithms for Decomposing Large-Scale Candidate Set into Pieces.☆67Updated last year
- tensorflow extend framework☆13Updated 4 years ago
- Implementation of CAN: Revisiting Feature Co-Action for Click-Through RatePrediction☆210Updated 3 years ago
- report reading paper list☆92Updated 5 years ago
- DNN framework based on ps-lite☆29Updated 3 years ago
- 计算广告机制策略相关材料整理(A collection of research and application papers about Strategy in Internet advertising.)☆143Updated 9 months ago
- ☆285Updated 5 years ago
- Implement Wide & Deep algorithm by using NumPy☆150Updated 5 years ago
- Fast Greedy MAP Inference for DPP☆122Updated 4 years ago
- ☆36Updated 3 years ago
- Classical RecSys algorithms implemented by using TensorFlow Estimators☆183Updated 6 years ago
- CTR模型代码和学习笔记总结☆377Updated 3 years ago
- Distributed FM and LR based on Parameter Server with Ftrl☆128Updated 7 years ago
- ☆194Updated 4 years ago
- 在常规推荐系统算法和系统双优化的范式下，一线公司针对单个任务或单个业务的效果挖掘几乎达到极限。从2019年我们开始关注多种信息的萃取融合，提出了OneRec算法，希望通过平台或外部各种各样的信息来进行知识集成，打破数据孤岛，极大扩充推荐的“Extra World Knowl…☆99Updated this week
- 《互联网大厂推荐算法实战》资料库☆217Updated last year
- 主流推荐系统Rank算法的实现☆194Updated last year
- Multi-thread implementation of Factorization Machines with FTRL for multi-class classification problem which uses softmax as hypothesis.☆70Updated 3 years ago
- Source code and dataset for KDD 2020 paper "Controllable Multi-Interest Framework for Recommendation"☆281Updated 3 years ago
- sparse word2vec☆109Updated 2 years ago
- Deep Interest Network for Click-Through Rate Prediction / Deep Interest Evolution Network for Click-Through Rate Prediction☆75Updated 4 years ago
- ☆59Updated 3 years ago
- PyTorch On Angel, arming PyTorch with a powerful Parameter Server, which enable PyTorch to train very big models.☆165Updated last year
- I have surveyed the technology and papers of CTR & Recommender System, and implemented 25 common-used models with Pytorch for reusage. …☆39Updated last year