UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale

• URL: http://arxiv.org/abs/2606.00422v1
• Date: Fri, 29 May 2026 23:17:34 GMT
• Title: UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
• Abstract summary: We present UniPinRec, which achieves full-stack unification of retrieval and ranking at Pinterest.<n>UniPinRec delivers approximately +1% online engagement lift while cutting end-to-end serving latency by 11.1% and lifting QPS by 63.6%.
• Score: 13.323495829411577
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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, and serving cost. Prior work unifies the model architecture but not the full pipeline: input formats, training procedures, and serving stacks remain fragmented across stages. We present UniPinRec, which achieves full-stack unification of retrieval and ranking at Pinterest: one input format, one model, one training stage, deployed within existing serving infrastructure. A shared transformer encodes the user action sequence into candidate-independent representations that branch into retrieval (ANN dot-product) and ranking (cross-attention) via task-specific heads. Three ideas make this work: (1) Masked Action Modeling (MAM) eliminates interleaving, enabling weight sharing without doubling context length; (2) Blended training examples pair action sequences with feedview impression slates to satisfy both objectives jointly; (3) Cross-stage KV cache sharing reuses user-history computation from retrieval for ranking, reducing total FLOPs versus serving two independent models. Deployed in the Pinterest core surfaces, UniPinRec delivers approximately +1% online engagement lift while cutting end-to-end serving latency by 11.1% and lifting QPS by 63.6%. To our knowledge, this is the first full-stack unification of retrieval and ranking, covering inputs, model, training and serving, deployed in a production recommendation system.

Related papers

• OneModel: A Unified Foundation for Platform-Scale Multi-Scenario Ranking [11.905656321952394]
  We propose textbfOneModel, a unified framework for multi-stream final ranking.<n>OneModel maps heterogeneous behaviors into shared event sequences, learns long-context user representations with an action-oriented backbone.<n>We deploy OneModel in production at emphXiaohongshu, where it delivers consistent offline gains over strong baselines.
  arXiv  Detail & Related papers  (2026-08-19T06:50:47Z)
• Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers [71.99661189378442]
  A transformer-based model can be made smaller in three ways.<n>A single object names any size the model can run at, and a short schedule lists the sizes to train.<n>The same abstraction covers both retrievers and rerankers and both encoder and decoder models.
  arXiv  Detail & Related papers  (2026-08-09T16:45:28Z)
• Unifying Generative Recall and Multi-Objective Ranking in a Single Decoder-Only Sequence [26.231002784432842]
  generative recall and ranking scaling share a common Transformer-based modeling philosophy.<n>We propose textbfUniR$2$, a textbfUnified decoder-only Transformer that unifies Generative textbfRecall and Multi-Objective textbfRanking.
  arXiv  Detail & Related papers  (2026-07-27T13:47:38Z)
• Selectivity Drives Efficiency: Dataset Pruning for Visual Place Recognition [52.52131290631774]
  We propose a place-wise dataset pruning framework tailored for visual place recognition (VPR)<n>Our method treats each place as the basic pruning unit and introduces two novel metrics, i.e., intra-place diversity (IPD) and inter-place similarity (IPS)<n>Experiments demonstrate that our method consistently outperforms state-of-the-art DP baselines under different pruning ratios.
  arXiv  Detail & Related papers  (2026-07-16T12:16:00Z)
• Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition [53.005382593686356]
  Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision.<n>We study this setting through subject-level machine unlearning as a post-hoc sanitization mechanism for engagement recognition.
  arXiv  Detail & Related papers  (2026-05-06T10:03:06Z)
• ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression [5.223477157195793]
  "lost in the middle" phenomenon degrades ranking quality as input length grows.<n>Inference latency scales super-linearly with sequence length, rendering listwise reranking impractical for industrial deployment.<n>We present ResRank, a unified retrieval-reranking framework that fundamentally addresses both challenges.
  arXiv  Detail & Related papers  (2026-04-24T03:11:51Z)
• GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation [14.663434490160016]
  We present GenRec, a preference-oriented generative framework deployed on the JD App.<n>In month-long online A/B tests, GenRec achieves 9.5% improvement in click count and 8.7% in transaction count over the existing pipeline.
  arXiv  Detail & Related papers  (2026-04-16T11:07:05Z)
• SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling [58.05959902776133]
  We introduce Single-Pass.<n>with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation.<n>We demonstrate SPARE's effectiveness across four diverse datasets spanning mathematical reasoning (GSM8K, MATH), multi-hop question answering (MuSiQue-Ans), and spatial reasoning (SpaRP)<n>On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only $sim$16% of training samples compared to human-labeled and other synthetically trained baselines.
  arXiv  Detail & Related papers  (2025-06-18T14:37:59Z)
• List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation [80.12531449946655]
  We propose a Reranking-Truncation joint model (GenRT) that can perform the two tasks concurrently. GenRT integrates reranking and truncation via generative paradigm based on encoder-decoder architecture. Our method achieves SOTA performance on both reranking and truncation tasks for web search and retrieval-augmented LLMs.
  arXiv  Detail & Related papers  (2024-02-05T06:52:53Z)
• UniParser: Multi-Human Parsing with Unified Correlation Representation Learning [18.372259148872228]
  This paper introduces Uni, which integrates instance-level and category-level representations in three key aspects. Uni achieves 49.3% AP on MHPv2.0 and 60.4% AP on CIHP.
  arXiv  Detail & Related papers  (2023-10-13T10:03:01Z)
• Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer [80.50327229467993]
  We show that a single model trained end-to-end can achieve both competitive retrieval and QA performance. We show that end-to-end adaptation significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings.
  arXiv  Detail & Related papers  (2022-12-05T04:51:21Z)
• Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition [80.74495836502919]
  In this work, we focus on joint human fashion segmentation and attribute recognition. We introduce the object query for segmentation and the attribute query for attribute prediction. For attribute stream, we design a novel Multi-Layer Rendering module to explore more fine-grained features.
  arXiv  Detail & Related papers  (2022-04-10T11:11:10Z)
• Jigsaw Clustering for Unsupervised Visual Representation Learning [68.09280490213399]
  We propose a new jigsaw clustering pretext task in this paper. Our method makes use of information from both intra- and inter-images. It is even comparable to the contrastive learning methods when only half of training batches are used.
  arXiv  Detail & Related papers  (2021-04-01T08:09:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.