Efficient few-shot learning with Sentence Transformers

We write sample code for two tower models for retrieval and add RLHF/RLAIF style alignment with a ranking model to make the retrieval more aligned with the ranking model on top

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

✨✨Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

Multiple ways to model user preference in recommender systems

Qdrant - Vector Database for the next generation of AI applications. Also available in the cloud https://cloud.qdrant.io/

Two-Tower recommendation model in PyTorch (educational)

MTReclib provides a PyTorch implementation of multi-task recommendation models and common datasets.

This is a pytorch implementation for the BST model from Alibaba https://arxiv.org/pdf/1905.06874.pdf

TensorFlow implementation of multi-task learning architectures, incl. MMoE & PLE, on wechat dataset

multi task mode for esmm and mmoe

PyTorch Implementation of the Multi-gate Mixture-of-Experts with Exclusivity (MMoEEx)

Awesome Deep Learning papers for industrial Search, Recommendation and Advertising. They focus on Embedding, Matching, Ranking (CTR prediction, CVR prediction), Post Ranking, Transfer, Reinforcemen…

PyTorch implementation of moe, which stands for mixture of experts

Recommender Systems Paperlist that I am interested in

深度学习相关的模型训练、评估和预测相关代码

MMoE-TF2.0

a multitask ranking system

Make Opensource Easy - tools for synchronizing repositories

An industrial deep learning framework for high-dimension sparse data

A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error ＝ 0.34%.

A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization (NAACL 2019)

存放推荐算法相关代码、文档、资料

Deep Scalable Sparse Tensor Network Engine (DSSTNE) is an Amazon developed library for building Deep Learning (DL) machine learning (ML) models

A Keras implementation of "Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts" (KDD 2018)