Zhe Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zhe Wang has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Jingjian Lin
ByteDance Search, Beijing, China
4 shared publications - Shikang Wu
ByteDance Search, Beijing, China
4 shared publications - Shiyong Hong
ByteDance Search, Beijing, China
3 shared publications - Yuchao Zheng
ByteDance, Hangzhou, China
3 shared publications - Jia Cheng
Meituan, Beijing, China
2 shared publications - Jingyue Gao
Alibaba Group, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8276-8284
LEMUR: Large scale End-to-end MUltimodal Recommendation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8276-8284
Open AccessLEMUR: Large scale End-to-end MUltimodal Recommendation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8258-8266
MSN: A Memory-based Sparse Activation Scaling Framework for Large-scale Industrial Recommendation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8258-8266
Open AccessMSN: A Memory-based Sparse Activation Scaling Framework for Large-scale Industrial Recommendation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7809-7817
MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7809-7817
Open AccessMDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 590-599
HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction
Industrial large-scale recommendation models (LRMs) face the challenge of jointly modeling long-range user behavior sequences and heterogeneous non-sequential features under strict efficiency constraints. However, most existing architectures employ a decoupled pipeline: long sequences are first compressed with a query-token based sequence compressor like LONGER, followed by fusion with dense features through token-mixing modules like RankMixer, which thereby limits both the representation capacity and the interaction flexibility. This paper presents HyFormer, a unified hybrid transformer architecture that tightly integrates long-sequence modeling and feature interaction into a single backbone. From the perspective of sequence modeling, we revisit and redesign query tokens in LRMs, and frame the LRM modeling task as an alternating optimization process that integrates two core components: Query Decoding which expands non-sequential features into Global Tokens and performs long sequence decoding over layer-wise key-value representations of long behavioral sequences; and Query Boosting which enhances cross-query and cross-sequence heterogeneous interactions via efficient token mixing. The two complementary mechanisms are performed iteratively to refine semantic representations across layers. Extensive experiments on billion-scale industrial datasets demonstrate that HyFormer consistently outperforms strong LONGER and RankMixer baselines under comparable parameter and FLOPs budgets, while exhibiting superior scaling behavior with increasing parameters and FLOPs. Large-scale online A/B tests in high-traffic production systems further validate its effectiveness, showing significant gains over deployed state-of-the-art models. These results highlight the practicality and scalability of HyFormer as a unified modeling framework for industrial LRMs.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 590-599
Open AccessHyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction
Industrial large-scale recommendation models (LRMs) face the challenge of jointly modeling long-range user behavior sequences and heterogeneous non-sequential features under strict efficiency constraints. However, most existing architectures employ a decoupled pipeline: long sequences are first compressed with a query-token based sequence compressor like LONGER, followed by fusion with dense features through token-mixing modules like RankMixer, which thereby limits both the representation capacity and the interaction flexibility. This paper presents HyFormer, a unified hybrid transformer architecture that tightly integrates long-sequence modeling and feature interaction into a single backbone. From the perspective of sequence modeling, we revisit and redesign query tokens in LRMs, and frame the LRM modeling task as an alternating optimization process that integrates two core components: Query Decoding which expands non-sequential features into Global Tokens and performs long sequence decoding over layer-wise key-value representations of long behavioral sequences; and Query Boosting which enhances cross-query and cross-sequence heterogeneous interactions via efficient token mixing. The two complementary mechanisms are performed iteratively to refine semantic representations across layers. Extensive experiments on billion-scale industrial datasets demonstrate that HyFormer consistently outperforms strong LONGER and RankMixer baselines under comparable parameter and FLOPs budgets, while exhibiting superior scaling behavior with increasing parameters and FLOPs. Large-scale online A/B tests in high-traffic production systems further validate its effectiveness, showing significant gains over deployed state-of-the-art models. These results highlight the practicality and scalability of HyFormer as a unified modeling framework for industrial LRMs.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4974-4980
COPR: Consistency-Oriented Pre-Ranking for Online Advertising
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4974-4980
Open AccessCOPR: Consistency-Oriented Pre-Ranking for Online Advertising
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3948-3952
Deep Context Interest Network for Click-Through Rate Prediction
Click-Through Rate (CTR) prediction, estimating the probability of a user clicking on an item, is essential in industrial applications, such as online advertising. Many works focus on user behavior modeling to improve CTR prediction performance. However, most of those methods only model users' positive interests from users' click items while ignoring the context information, which is the display items around the clicks, resulting in inferior performance. In this paper, we highlight the importance of context information on user behavior modeling and propose a novel model named Deep Context Interest Network (DCIN), which integrally models the click and its display context to learn users' context-aware interests. DCIN consists of three key modules: 1) Position-aware Context Aggregation Module (PCAM), which performs aggregation of display items with an attention mechanism; 2) Feedback-Context Fusion Module (FCFM), which fuses the representation of clicks and display contexts through non-linear feature interaction; 3) Interest Matching Module (IMM), which activates interests related with the target item. Moreover, we provide our hands-on solution to implement DCIN on large-scale industrial systems. The significant improvements in both offline and online evaluations demonstrate the superiority of our proposed DCIN method. Notably, DCIN has been deployed on our online advertising system serving the main traffic, which brings 1.5% CTR and 1.5% RPM lift.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3948-3952
Open AccessDeep Context Interest Network for Click-Through Rate Prediction
Click-Through Rate (CTR) prediction, estimating the probability of a user clicking on an item, is essential in industrial applications, such as online advertising. Many works focus on user behavior modeling to improve CTR prediction performance. However, most of those methods only model users' positive interests from users' click items while ignoring the context information, which is the display items around the clicks, resulting in inferior performance. In this paper, we highlight the importance of context information on user behavior modeling and propose a novel model named Deep Context Interest Network (DCIN), which integrally models the click and its display context to learn users' context-aware interests. DCIN consists of three key modules: 1) Position-aware Context Aggregation Module (PCAM), which performs aggregation of display items with an attention mechanism; 2) Feedback-Context Fusion Module (FCFM), which fuses the representation of clicks and display contexts through non-linear feature interaction; 3) Interest Matching Module (IMM), which activates interests related with the target item. Moreover, we provide our hands-on solution to implement DCIN on large-scale industrial systems. The significant improvements in both offline and online evaluations demonstrate the superiority of our proposed DCIN method. Notably, DCIN has been deployed on our online advertising system serving the main traffic, which brings 1.5% CTR and 1.5% RPM lift.
- Top Cited PapersOpen Access
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 508-516
DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
Point-of-Interest (POI) recommendation plays a vital role in various location-aware services. It has been observed that POI recommendation is driven by both sequential and geographical influences. However, since there is no annotated label of the dominant influence during recommendation, existing methods tend to entangle these two influences, which may lead to sub-optimal recommendation performance and poor interpretability. In this paper, we address the above challenge by proposing DisenPOI, a novel Disentangled dual-graph framework for POI recommendation, which jointly utilizes sequential and geographical relationships on two separate graphs and disentangles the two influences with self-supervision. The key novelty of our model compared with existing approaches is to extract disentangled representations of both sequential and geographical influences with contrastive learning. To be specific, we construct a geographical graph and a sequential graph based on the check-in sequence of a user. We tailor their propagation schemes to become sequence-/geo-aware to better capture the corresponding influences. Preference proxies are extracted from check-in sequence as pseudo labels for the two influences, which supervise the disentanglement via a contrastive loss. Extensive experiments on three datasets demonstrate the superiority of the proposed model.
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 508-516
Top Cited PapersOpen AccessDisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
Point-of-Interest (POI) recommendation plays a vital role in various location-aware services. It has been observed that POI recommendation is driven by both sequential and geographical influences. However, since there is no annotated label of the dominant influence during recommendation, existing methods tend to entangle these two influences, which may lead to sub-optimal recommendation performance and poor interpretability. In this paper, we address the above challenge by proposing DisenPOI, a novel Disentangled dual-graph framework for POI recommendation, which jointly utilizes sequential and geographical relationships on two separate graphs and disentangles the two influences with self-supervision. The key novelty of our model compared with existing approaches is to extract disentangled representations of both sequential and geographical influences with contrastive learning. To be specific, we construct a geographical graph and a sequential graph based on the check-in sequence of a user. We tailor their propagation schemes to become sequence-/geo-aware to better capture the corresponding influences. Preference proxies are extracted from check-in sequence as pseudo labels for the two influences, which supervise the disentanglement via a contrastive loss. Extensive experiments on three datasets demonstrate the superiority of the proposed model.