PinRec: Outcome-Conditioned, Multi-Token Generative Retrieval for Industry-Scale Recommendation Systems
Generative retrieval methods utilize generative sequential modeling techniques, such as transformers, to generate candidate items for recommender systems. These methods have demonstrated promising results in academic benchmarks, surpassing traditional retrieval models like two-tower architectures. However, current generative retrieval methods lack the scalability required for industrial recommender systems, and they are insufficiently flexible to satisfy the multiple metric requirements of modern systems. This paper introduces PinRec, a novel generative retrieval model developed for applications at Pinterest. PinRec utilizes outcome-conditioned generation, enabling modelers to specify how to balance various outcome metrics, such as the number of saves and clicks, to effectively align with business goals and user exploration. Additionally, PinRec incorporates multi-token generation to enhance output diversity while optimizing generation. Our experiments demonstrate that PinRec can successfully balance performance, diversity, and efficiency, delivering a significant positive impact to users using generative models. This paper marks a significant milestone in generative retrieval, as it presents, to our knowledge, the first rigorous study on implementing generative retrieval at the scale of Pinterest.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityRecommendation SystemsRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Fidelity-Aware Recommendation Explanations via Stochastic Path Integration
Explanation fidelity, which measures how accurately an explanation reflects a model's true reasoning, remains critically underexplored in recommender systems. We introduce SPINRec (Stochastic Path Integration for Neural …
UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
Modern recommendation systems predominantly train retrieval and ranking as separate models despite both increasingly relying on large transformers encoding the same user behavior data, duplicating parameters, compute, an…
Recommendation SystemsText-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models
Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their gener…
Image GenerationText to Image GenerationText-to-Image GenerationLatent Denoising Makes Good Tokenizers
Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective --…
Image GenerationEfficient Generative Prediction for EHR Foundation Models: The SCOPE and REACH Estimators
Generative foundation models trained on tokenized electronic health record (EHR) timelines show promise for clinical outcome prediction via Monte Carlo sampling of simulated future trajectories. However, this approach su…