HSTU-based generative recommenders with 1.5 trillion parameters scale as a power law with compute up to GPT-3 scale, outperform baselines by up to 65.8% NDCG, run 5-15x faster than FlashAttention2 on long sequences, and improve online A/B metrics by 12.4%.
arXiv preprint arXiv:2306.04039 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Cluster-based real-time out-of-batch negatives drawn from LLM media embeddings outperform industry-standard negative sampling for two-tower retrieval and cut popularity bias.
citing papers explorer
-
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
HSTU-based generative recommenders with 1.5 trillion parameters scale as a power law with compute up to GPT-3 scale, outperform baselines by up to 65.8% NDCG, run 5-15x faster than FlashAttention2 on long sequences, and improve online A/B metrics by 12.4%.
-
Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval
Cluster-based real-time out-of-batch negatives drawn from LLM media embeddings outperform industry-standard negative sampling for two-tower retrieval and cut popularity bias.