Institution profile

Pinterest

Industry researchnorthamerica · us
Official website
Research library46linked papers
Opportunities37open roles
Selected work

Representative Papers

Privacy Preserving Conversion Modeling in Data Clean Room

Oct 08, 2024ACM Conference on Recommender Systems

In data clean room settings, CVR prediction faces dual constraints: stringent user privacy protection and the requirement that advertisers’ data remain within their own domain. To address this, we propose the first collaborative training framework integrating batch-level gradient aggregation, Adapter-based efficient fine-tuning, and label differential privacy with bias mitigation. Without sharing raw labels or model parameters, our method enables cross-domain joint modeling via gradient-level collaboration: batch-wise gradient aggregation ensures regulatory compliance; lightweight Adapters enable low-overhead domain adaptation; and bias-corrected label differential privacy mitigates estimation bias induced by noise injection. Evaluated on industrial datasets, our approach achieves state-of-the-art ROC-AUC performance while reducing communication overhead by 62%. It strictly adheres to GDPR and other privacy regulations, fulfilling practical commercial deployment requirements.

1 citationsRead paper

Evaluating for the long term: Learnings from industry

Aug 08, 2026

Short-term online experiments often fail to accurately predict long-term business outcomes, potentially leading to decisions misaligned with strategic objectives. Drawing on insights from industry expert workshops, this work proposes a design principle for surrogate metrics centered on decision utility rather than solely on unbiasedness, advocating that interpretable, experiment-driven simple surrogates outperform complex black-box models. Through expert consensus synthesis, surrogate metric analysis, and comparative evaluation of experimental versus observational data, the study systematically outlines a methodology for constructing effective surrogates and uncovers a critical relationship between the stability of long-term effects and surrogate validity. While underscoring the irreplaceable value of high-quality long-term experimentation, the research also delineates core challenges and practical guidelines for surrogate learning in real-world settings.

0 citationsRead paper

Advancing Relevance Measurement with Vision-Language Models for Web-Scale Search

Aug 03, 2026

This work addresses the high cost and prolonged turnaround of manual relevance labeling, which hinder large-scale online search experimentation. To overcome these limitations, the study introduces vision-language models (VLMs) into industrial search relevance evaluation for the first time, establishing an automated labeling pipeline deployed in Pinterest’s online A/B experiments. The proposed approach substantially improves evaluation efficiency and coverage, enabling more granular sampling strategies and reducing the minimum detectable effect (MDE). Empirical results demonstrate strong agreement between VLM-generated relevance judgments and human annotations, confirming the method’s capacity to support high-quality, high-sensitivity assessment of search systems at scale.

0 citationsRead paper

PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest

Jul 24, 2026

This work addresses the challenges of content cold-start and exposure bias in industrial-scale search and recommendation systems by proposing the first unified exploration and debiasing architecture that spans the entire funnel across multiple stages, applicable to both search and recommendation scenarios. The approach integrates multi-stage modeling, content debiasing algorithms, a controllable online exploration mechanism, and a scalable causal evaluation framework, enabling efficient exploration of new content while maintaining control over short-term performance metrics. Deployed at Pinterest for two years, the system has significantly improved the exposure efficiency of new content, enhanced user engagement, and fostered overall ecosystem health, while supporting rapid experimental iteration and long-term optimization.

0 citationsRead paper
Recent publications

Latest Papers

Evaluating for the long term: Learnings from industry

Aug 08, 2026

Short-term online experiments often fail to accurately predict long-term business outcomes, potentially leading to decisions misaligned with strategic objectives. Drawing on insights from industry expert workshops, this work proposes a design principle for surrogate metrics centered on decision utility rather than solely on unbiasedness, advocating that interpretable, experiment-driven simple surrogates outperform complex black-box models. Through expert consensus synthesis, surrogate metric analysis, and comparative evaluation of experimental versus observational data, the study systematically outlines a methodology for constructing effective surrogates and uncovers a critical relationship between the stability of long-term effects and surrogate validity. While underscoring the irreplaceable value of high-quality long-term experimentation, the research also delineates core challenges and practical guidelines for surrogate learning in real-world settings.

0 citationsRead paper

Advancing Relevance Measurement with Vision-Language Models for Web-Scale Search

Aug 03, 2026

This work addresses the high cost and prolonged turnaround of manual relevance labeling, which hinder large-scale online search experimentation. To overcome these limitations, the study introduces vision-language models (VLMs) into industrial search relevance evaluation for the first time, establishing an automated labeling pipeline deployed in Pinterest’s online A/B experiments. The proposed approach substantially improves evaluation efficiency and coverage, enabling more granular sampling strategies and reducing the minimum detectable effect (MDE). Empirical results demonstrate strong agreement between VLM-generated relevance judgments and human annotations, confirming the method’s capacity to support high-quality, high-sensitivity assessment of search systems at scale.

0 citationsRead paper

PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest

Jul 24, 2026

This work addresses the challenges of content cold-start and exposure bias in industrial-scale search and recommendation systems by proposing the first unified exploration and debiasing architecture that spans the entire funnel across multiple stages, applicable to both search and recommendation scenarios. The approach integrates multi-stage modeling, content debiasing algorithms, a controllable online exploration mechanism, and a scalable causal evaluation framework, enabling efficient exploration of new content while maintaining control over short-term performance metrics. Deployed at Pinterest for two years, the system has significantly improved the exposure efficiency of new content, enhanced user engagement, and fostered overall ecosystem health, while supporting rapid experimental iteration and long-term optimization.

0 citationsRead paper

Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning

Jul 15, 2026

This work addresses the challenge of directly optimizing long-term user retention in recommender systems, where signals are sparse, delayed, and difficult to attribute. The authors propose a model-agnostic downstream reward learning framework that constructs a unified and generalizable proxy reward by offline selection of early-observable, highly predictive multi-source user behaviors. This proxy reward is seamlessly integrated into ranking models to optimize long-term user value, circumventing the need for task-specific reward engineering or complex sequential modeling. Evaluated through extensive A/B experiments across multiple core scenarios at Pinterest, the approach significantly improves user engagement and retention metrics and has been successfully deployed in production.

0 citationsRead paper