All Stories

  1. Improving Data Efficiency for Recommenders and LLMs
  2. Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems
  3. Self-Auxiliary Distillation for Sample Efficient Learning in Google-Scale Recommenders
  4. Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations
  5. Serving Large User Sequence Models in Large Scale Applications
  6. Co-optimize Content Generation and Consumption in a Large Scale Video Recommendation System
  7. Multi-Task Neural Linear Bandit for Exploration in Recommender Systems
  8. Large Language Models as Data Augmenters for Cold-Start Item Recommendation
  9. Cluster Anchor Regularization to Alleviate Popularity Bias in Recommender Systems
  10. Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses
  11. Long-Term Value of Exploration: Measurements, Findings and Algorithms
  12. Multitask Ranking System for Immersive Feed and No More Clicks: A Case Study of Short-Form Video Recommendation
  13. Online Matching: A Real-time Bandit System for Large-scale Recommendations
  14. Efficient Data Representation Learning in Google-scale Systems
  15. Improving Training Stability for Multitask Ranking Models in Recommender Systems
  16. Empowering Long-tail Item Recommendation through Cross Decoupling Network (CDN)
  17. Fresh Content Needs More Attention: Multi-funnel Fresh Content Recommendation
  18. HyperFormer: Learning Expressive Sparse Feature Representations via Hypergraph Transformer
  19. Investigating Action-Space Generalization in Reinforcement Learning for Recommendation Systems
  20. Latent User Intent Modeling for Sequential Recommenders
  21. Off-Policy Actor-critic for Recommender Systems
  22. Surrogate for Long-Term User Experience in Recommender Systems
  23. Distributionally-robust Recommendations for Improving Worst-case User Experience
  24. Learning to Augment for Casual User Recommendation
  25. Can Small Heads Help? Understanding and Improving Multi-Task Generalization
  26. Multi-Resolution Attention for Personalized Item Search
  27. Self-supervised Learning for Large-scale Item Recommendations
  28. Values of User Exploration in Recommender Systems
  29. Learning to Embed Categorical Features without Embedding Tables for Recommendation
  30. Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning
  31. Measuring Model Fairness under Noisy Covariates: A Theoretical Perspective
  32. DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
  33. Towards Content Provider Aware Recommender Systems
  34. A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation
  35. User Response Models to Improve a REINFORCE Recommender System
  36. Beyond Point Estimate: Inferring Ensemble Prediction Variation from Neuron Activation Strength in Recommender Systems
  37. Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval
  38. Deconfounding User Satisfaction Estimation from Response Rate Bias
  39. End-to-End Deep Attentive Personalized Item Retrieval for Online Content-sharing Platforms
  40. Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations
  41. Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems
  42. Off-policy Learning in Two-stage Recommender Systems
  43. Recommending what video to watch next
  44. Sampling-bias-corrected neural modeling for large corpus item recommendations
  45. Quantifying Long Range Dependence in Language and User Behavior to improve RNNs
  46. Fairness in Recommendation Ranking through Pairwise Comparisons
  47. Towards Neural Mixture Recommender for Long Range Dependent User Sequences
  48. Top-K Off-Policy Correction for a REINFORCE Recommender System
  49. Practical Diversified Recommendations on YouTube with Determinantal Point Processes
  50. Q&R
  51. Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
  52. Evaluation and Refinement of Clustered Search Results with the Crowd
  53. The Case for Learned Index Structures
  54. Latent Cross
  55. Design for Searching & Finding
  56. Instant foodie