Zhangang Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhangang Lin has a total of 96 co-authors. Here are the top co-authors by number of shared publications:
- Jingping Shao
JD, Beijing, China
18 shared publications - Changping Peng
JD.com, Beijing, China
17 shared publications - Congcong Liu
JD.com, Beijing, China
9 shared publications - Ching Law
JD.com, Beijing, China
8 shared publications - Jie He
JD.com, Beijing, China
6 shared publications - Xiwei Zhao
JD.com, Beijing, China
6 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8728-8735
TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8728-8735
Open AccessTUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 19-30
Auto-bidding under Return-on-Spend Constraints with Uncertainty Quantification
Auto-bidding systems are widely used in advertising to automatically determine bid values under constraints such as total budget and Return-on-Spend (RoS) targets. Existing works often assume that the value of an ad impression, such as the conversion rate, is known. This paper considers the more realistic scenario where the true value is unknown. We propose a novel method that uses conformal prediction to quantify the uncertainty of these values based on machine learning methods trained on historical bidding data with contextual features, without assuming the data are i.i.d. This approach is compatible with current industry systems that use machine learning to predict values. Building on prediction intervals, we introduce an adjusted value estimator derived from machine learning predictions, and show that it provides performance guarantees without requiring knowledge of the true value. We apply this method to enhance existing auto-bidding algorithms with budget and RoS constraints, and establish theoretical guarantees for achieving high reward while keeping RoS violations low. Empirical results on both simulated and real-world industrial datasets demonstrate that our approach improves performance while maintaining computational efficiency.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 19-30
Open AccessAuto-bidding under Return-on-Spend Constraints with Uncertainty Quantification
Auto-bidding systems are widely used in advertising to automatically determine bid values under constraints such as total budget and Return-on-Spend (RoS) targets. Existing works often assume that the value of an ad impression, such as the conversion rate, is known. This paper considers the more realistic scenario where the true value is unknown. We propose a novel method that uses conformal prediction to quantify the uncertainty of these values based on machine learning methods trained on historical bidding data with contextual features, without assuming the data are i.i.d. This approach is compatible with current industry systems that use machine learning to predict values. Building on prediction intervals, we introduce an adjusted value estimator derived from machine learning predictions, and show that it provides performance guarantees without requiring knowledge of the true value. We apply this method to enhance existing auto-bidding algorithms with budget and RoS constraints, and establish theoretical guarantees for achieving high reward while keeping RoS violations low. Empirical results on both simulated and real-world industrial datasets demonstrate that our approach improves performance while maintaining computational efficiency.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 7712-7723
A Generative Contextual Comprehension Paradigm for Takeout Ranking Model
The ranking stage serves as the central optimization and allocation hub in advertising systems, governing economic value distribution through eCPM and orchestrating the user-centric blending of organic and advertising content. Prevailing ranking models often rely on fragmented modules and hand-crafted features, limiting their ability to interpret complex user intent. This challenge is further amplified in location-based services such as food delivery, where user decisions are shaped by dynamic spatial, temporal, and individual contexts. To address these limitations, we propose a novel generative framework that reframes ranking as a context comprehension task, modeling heterogeneous signals in a unified architecture. Our architecture consists of two core components: the Generative Contextual Encoder (GCE) and the Generative Contextual Fusion (GCF). The GCE comprises three specialized modules: a Personalized Context Enhancer (PCE) for user-specific modeling, a Collective Context Enhancer (CCE) for group-level patterns, and a Dynamic Context Enhancer (DCE) for real-time situational adaptation. The GCF module then seamlessly integrates these contextual representations through low-rank adaptation. Extensive experiments confirm that our method achieves significant gains in critical business metrics, including click-through rate and platform revenue. We have successfully deployed our method on a large-scale food delivery advertising platform, demonstrating its substantial practical impact. This work pioneers a new perspective on generative recommendation and highlights its practical potential in industrial advertising systems.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 7712-7723
Open AccessA Generative Contextual Comprehension Paradigm for Takeout Ranking Model
The ranking stage serves as the central optimization and allocation hub in advertising systems, governing economic value distribution through eCPM and orchestrating the user-centric blending of organic and advertising content. Prevailing ranking models often rely on fragmented modules and hand-crafted features, limiting their ability to interpret complex user intent. This challenge is further amplified in location-based services such as food delivery, where user decisions are shaped by dynamic spatial, temporal, and individual contexts. To address these limitations, we propose a novel generative framework that reframes ranking as a context comprehension task, modeling heterogeneous signals in a unified architecture. Our architecture consists of two core components: the Generative Contextual Encoder (GCE) and the Generative Contextual Fusion (GCF). The GCE comprises three specialized modules: a Personalized Context Enhancer (PCE) for user-specific modeling, a Collective Context Enhancer (CCE) for group-level patterns, and a Dynamic Context Enhancer (DCE) for real-time situational adaptation. The GCF module then seamlessly integrates these contextual representations through low-rank adaptation. Extensive experiments confirm that our method achieves significant gains in critical business metrics, including click-through rate and platform revenue. We have successfully deployed our method on a large-scale food delivery advertising platform, demonstrating its substantial practical impact. This work pioneers a new perspective on generative recommendation and highlights its practical potential in industrial advertising systems.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5923-5930
SMTIR: Scenario-Aware Multi-Trigger Induction Network for CTR Prediction
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5923-5930
Open AccessSMTIR: Scenario-Aware Multi-Trigger Induction Network for CTR Prediction
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1086-1090
Stream Normalization for CTR Prediction
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1086-1090
Open AccessStream Normalization for CTR Prediction
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4555-4565
UniERF: A Uniform Embedding-based Retrieval Framework for E-commerce Search
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4555-4565
Open AccessUniERF: A Uniform Embedding-based Retrieval Framework for E-commerce Search
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4249-4253
Post-event Modeling via Causal Optimal Transport for CTR Prediction
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4249-4253
Open AccessPost-event Modeling via Causal Optimal Transport for CTR Prediction
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4299-4303
Multi-objective Aligned Bidword Generation Model for E-commerce Search Advertising
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4299-4303
Open AccessMulti-objective Aligned Bidword Generation Model for E-commerce Search Advertising
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4219-4223
Graph Isomorphism Network-Based Cohort Modeling In Click-Through Rate Prediction
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4219-4223
Open AccessGraph Isomorphism Network-Based Cohort Modeling In Click-Through Rate Prediction
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4259-4263
ADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4259-4263
Open AccessADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce