主要分享一下自己在学习推荐系统/计算广告的学习路程以及相关资源
优秀文章汇总
学习资源汇总
paper
【排序】大规模稀疏线性排序模型FTRL工程实现 Ad click prediction: a view from the trenches (http://www.eecs.tufts.edu/~dsculley/papers/ad-click-prediction.pdf)
【排序】GBDT LR融合模型 Practical Lessons from Predicting Clicks on Ads at Facebook(https://quinonero.net/Publications/predicting-clicks-facebook.pdf)
【排序】因子分解机，召回和排序的利器，速度快效果好 Factorization Machines(https://www.csie.ntu.edu.tw/~b97053/paper/Rendle2010FM.pdf)
【排序】深度学习模型Wide&Deep Wide & Deep Learning for Recommender Systems(https://arxiv.org/pdf/1606.07792)
【排序】深度兴趣网络DIN，捕获用户历史行为与候选物料相关性 Deep Interest Network for Click-Through Rate Prediction(https://arxiv.org/pdf/1706.06978)
【召回】基于内容的协同过滤及其变种可以说是召回中应用最广泛算法之一，这篇是最经典的ItemCF Amazon.com recommendations: item-to-item collaborative filtering(https://ieeexplore.ieee.org/document/1167344)
【召回】无监督embedding学习，用于向量召回 Item2vec: Neural Item Embedding for Collaborative Filtering(https://arxiv.org/pdf/1603.04259v2.pdf)
【召回】双塔DNN Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations(https://www.researchgate.net/publication/335768638_Sampling-bias-corrected_neural_modeling_for_large_corpus_item_recommendations)
【召回】Youtube DNN Deep neural networks for YouTube recommendations(https://www.researchgate.net/publication/307573656_Deep_Neural_Networks_for_YouTube_Recommendations)
- 【召回】考虑用户多峰兴趣的深度召回模型 Multi-Interest Network with Dynamic Routing for Recommendation at Tmall(https://arxiv.org/pdf/1904.08030)
- 【重排&机制策略】多样性重排MMR,这篇要告诉大家推荐系统中还需要很多机制策略 The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries(https://www.cs.cmu.edu/~jgc/publication/The_Use_MMR_Diversity_Based_LTMIR_1998.pdf)
转载自 公众号: 浅梦的学习笔记(weichennote)