Unified Semantic and ID Representation Learning for Deep Recommenders
混合距离用于量化匹配 & 端到端的联合训练
Generative
Generative Recommendation with Semantic IDs: A Practitioner’s Handbook
分析比较了现有生成式推荐的 Tricks 并给出了一个训练框架
Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
COBRA, 链接离散编码和稠密表示的尝试
Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation
LC-Rec, LLM + RQ-VAE + 丰富的多任务训练
OneRec: Unifying Retrieve and Rank with Generative Recommender and Preference Alignment
OneRec, 端到端的推荐模型
QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou
QARM, 多模态推荐对齐与量化
Unifying Generative and Dense Retrieval for Sequential Recommendation
LIGER, 生成式检索的冷启动缺陷与解决方案
Recommender Systems with Generative Retrieval
TIGER, 向量量化生成式检索