mlsanityData to 14 Oct 2026

Multi-Faceted Large Embedding Tables for Pinterest Ads Ranking

arXiv 2508.05700 ↗First posted 7 Aug 2025cs.IR cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Large embedding tables are indispensable in modern recommendation systems, thanks to their ability to effectively capture and memorize intricate details of interactions among diverse entities. As we explore integrating large embedding tables into Pinterest's ads ranking models, we encountered not only common challenges such as sparsity and scalability, but also several obstacles unique to our context. Notably, our initial attempts to train large embedding tables from scratch resulted in neutral metrics. To tackle this, we introduced a novel multi-faceted pretraining scheme that incorporates multiple pretraining algorithms. This approach greatly enriched the embedding tables and resulted in significant performance improvements. As a result, the multi-faceted large embedding tables bring great performance gain on both the Click-Through Rate (CTR) and Conversion Rate (CVR) domains. Moreover, we designed a CPU-GPU hybrid serving infrastructure to overcome GPU memory limits and elevate the scalability. This framework has been deployed in the Pinterest Ads system and achieved 1.34% online CPC reduction and 2.60% CTR increase with neutral end-to-end latency change.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

16 of 30 references.

References · 16

  1. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  2. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 327
  3. 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 320
  4. 2020PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterestcited by 75
  5. 2021MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Maskcited by 48
  6. 2019GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embeddingcited by 40
  7. 2020Learning to Embed Categorical Features without Embedding Tables for Recommendationcited by 38
  8. 2023FinalMLP: An Enhanced Two-Stream MLP Model for CTR Predictioncited by 37
  9. 2022Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Prediction Modelscited by 33
  10. 2023Embedding in Recommender Systems: A Surveycited by 20
  11. 2024On-Device Recommender Systems: A Comprehensive Surveycited by 20
  12. 2024OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Searchcited by 13
4 more
  1. 2023Rec4Ad: A Free Lunch to Mitigate Sample Selection Bias for Ads CTR Prediction in Taobaocited by 11
  2. 2022FiBiNet++: Reducing Model Size by Low Rank Feature Interaction Layer for CTR Predictioncited by 8
  3. 2025The Evolution of Embedding Table Optimization and Multi-Epoch Training in Pinterest Ads Conversioncited by 3
  4. 2025HybridServe: Efficient Serving of Large AI Models with Confidence-Based Cascade Routingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DUET -- Dual User Embedding Transformers for Offsite Conversion Predictioncited by 0