To Read

• https://netflixtechblog.com/improve-your-next-experiment-by-learning-better-proxy-metrics-from-past-experiments-64c786c2a3ac
• https://netflixtechblog.com/sequential-a-b-testing-keeps-the-world-streaming-netflix-part-1-continuous-data-cba6c7ed49df
• https://arxiv.org/abs/2407.02464
• https://arxiv.org/abs/2305.12102
• https://arxiv.org/abs/1709.03933
• https://arxiv.org/abs/2101.08769
• https://arxiv.org/abs/1205.2618 # BPR
• https://arxiv.org/abs/2312.08520 # InfoNCE+
• https://arxiv.org/abs/2308.06091 # MAWU
• https://arxiv.org/abs/2109.12613 # CCL
• https://arxiv.org/abs/2201.02327 # SSM
• https://arxiv.org/abs/2206.12811 # DirectAU
• KG-BERT
• XR-Transformer
• SetFit
• Lora vs Fine tuning
• Better Generalization with semantic IDs
• Mutual Information Neural Estimation
• Contrastive Learning with Hard Negatives
• Decoupled Contrastive Learning
• Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning
• Semi-Supervised Classification with Graph Convolutional Networks
• Ranking Distillation
• PinnerFormer
• BERT4Rec
• Retrieval as Attention
• Generate Rather than Retrieve
• PLM in Baidu Search
• Emebdding Based Retrieval in Facebook Search
• Self Attentive Sequential Recommendation
• Is BERT4Rec really better than SASRec?
• Transformers4Rec
• Pretrained Transformers for Text Ranking: BERT and Beyond
• Turning Dross Into Gold Loss: is BERT4Rec really better than SASRec?
• Modularized Transfomer-based Ranking Framework
• Pre-trained Language Model for Web-scale Retrieval in Baidu Search
• Related Pins at Pinterest: The Evolution of a Real-World Recommender System
• Improving Pinterest Search Relevance Using Large Language Models
• Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
• Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning
• Ranking Relevance in Yahoo Search
• Fine-Tuning LLaMA for Multi-Stage Text Retrieval
• Revisiting Deep Learning Models for Tabular Data
• OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search
• Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
• Behavior Sequence Transformer for E-commerce Recommendation in Alibaba
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest
• ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest
• RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses
• Pretrained Language Model based Web Search Ranking: From Relevance to Satisfaction
• Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline
• Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval
• SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
• Bootstrap your own latent: A new approach to self-supervised Learning
• Gradient Boosting Neural Networks: GrowNet
• GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning
• Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup