Hongbo Deng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongbo Deng has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Bo Zheng
Alibaba Group, Hangzhou, China
7 shared publications - Jian Xu
Alibaba Group, Hangzhou, China
6 shared publications - Wanxian Guan
Alibaba Group, Hangzhou, China
3 shared publications - Xubin Li
Alibaba Group
3 shared publications - Bin Tong
Alibaba Group, Hangzhou, China
2 shared publications - Bofang Li
Alibaba Group, Hangzhou, China
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 976-984
Alignment + Accuracy: The Cascade Reward Representation for Preranking
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 976-984
Open AccessAlignment + Accuracy: The Cascade Reward Representation for Preranking
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6177-6184
Dynamic Network-Based Two-Stage Time Series Forecasting for Affiliate Marketing
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6177-6184
Open AccessDynamic Network-Based Two-Stage Time Series Forecasting for Affiliate Marketing
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6169-6176
Audience-Aware and Self-Adaptive Multi-Interest Modeling for Sharing Rate Prediction in Affiliate Marketing
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6169-6176
Open AccessAudience-Aware and Self-Adaptive Multi-Interest Modeling for Sharing Rate Prediction in Affiliate Marketing
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 204-212
Gradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task Learning
Although multi-task learning (MTL) has been a preferred approach and successfully applied in many real-world scenarios, MTL models are not guaranteed to outperform single-task models on all tasks mainly due to the negative effects of conflicting gradients among the tasks. In this paper, we fully examine the influence of conflicting gradients and further emphasize the importance and advantages of achieving non-conflicting gradients which allows simple but effective trade-off strategies among the tasks with stable performance. Based on our findings, we propose the Gradient Deconfliction via Orthogonal Projections onto Subspaces (GradOPS) spanned by other task-specific gradients. Our method not only solves all conflicts among the tasks, but can also effectively search for diverse solutions towards different trade-off preferences among the tasks. Theoretical analysis on convergence is provided, and performance of our algorithm is fully testified on multiple benchmarks in various domains. Results demonstrate that our method can effectively find multiple state-of-the-art solutions with different trade-off strategies among the tasks on multiple datasets.
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 204-212
Open AccessGradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task Learning
Although multi-task learning (MTL) has been a preferred approach and successfully applied in many real-world scenarios, MTL models are not guaranteed to outperform single-task models on all tasks mainly due to the negative effects of conflicting gradients among the tasks. In this paper, we fully examine the influence of conflicting gradients and further emphasize the importance and advantages of achieving non-conflicting gradients which allows simple but effective trade-off strategies among the tasks with stable performance. Based on our findings, we propose the Gradient Deconfliction via Orthogonal Projections onto Subspaces (GradOPS) spanned by other task-specific gradients. Our method not only solves all conflicts among the tasks, but can also effectively search for diverse solutions towards different trade-off preferences among the tasks. Theoretical analysis on convergence is provided, and performance of our algorithm is fully testified on multiple benchmarks in various domains. Results demonstrate that our method can effectively find multiple state-of-the-art solutions with different trade-off strategies among the tasks on multiple datasets.
- Open Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 816-825
Unified Visual Preference Learning for User Intent Understanding
In the world of E-Commerce, the core task is to understand the personalized preference from various kinds of heterogeneous information, such as textual reviews, item images and historical behaviors. In current systems, these heterogeneous information are mainly exploited to generate better item or user representations. For example, in scenario of visual search, the importance of modeling query image has been widely acknowledged. But, these existing solutions focus on improving the representation quality of the query image, overlooking the personalized visual preference of the user. Note that the visual features affect the user's decision significantly, e.g., the user could be more likely to click the items with her preferred design. Hence, it is fruitful to exploit the visual preference to deliver better capacity for personalization. To this end, we propose a simple yet effective target-aware visual preference learning framework (named Tavern) for both item recommendation and search. The proposed Tavern works as an individual and generic model that can be smoothly plugged into different downstream systems. Specifically, for visual preference learning, we utilize the image of the target item to derive the visual preference signals for each historical clicked item. This procedure is modeled as a form of representation disentanglement, where the visual preference signals are extracted by taking off the noisy information irrelevant to visual preference from the shared visual information between the target and historical items. During this process, a novel selective orthogonality disentanglement is proposed to avoid the significant information loss. Then, a GRU network is utilized to aggregate these signals to form the final visual preference representation. Extensive experiments over three large-scale real-world datasets covering visual search, product search and recommendation well demonstrate the superiority of our proposed Tavern against existing technical alternatives. Further ablation study also confirms the validity of each design choice.
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 816-825
Open AccessUnified Visual Preference Learning for User Intent Understanding
In the world of E-Commerce, the core task is to understand the personalized preference from various kinds of heterogeneous information, such as textual reviews, item images and historical behaviors. In current systems, these heterogeneous information are mainly exploited to generate better item or user representations. For example, in scenario of visual search, the importance of modeling query image has been widely acknowledged. But, these existing solutions focus on improving the representation quality of the query image, overlooking the personalized visual preference of the user. Note that the visual features affect the user's decision significantly, e.g., the user could be more likely to click the items with her preferred design. Hence, it is fruitful to exploit the visual preference to deliver better capacity for personalization. To this end, we propose a simple yet effective target-aware visual preference learning framework (named Tavern) for both item recommendation and search. The proposed Tavern works as an individual and generic model that can be smoothly plugged into different downstream systems. Specifically, for visual preference learning, we utilize the image of the target item to derive the visual preference signals for each historical clicked item. This procedure is modeled as a form of representation disentanglement, where the visual preference signals are extracted by taking off the noisy information irrelevant to visual preference from the shared visual information between the target and historical items. During this process, a novel selective orthogonality disentanglement is proposed to avoid the significant information loss. Then, a GRU network is utilized to aggregate these signals to form the final visual preference representation. Extensive experiments over three large-scale real-world datasets covering visual search, product search and recommendation well demonstrate the superiority of our proposed Tavern against existing technical alternatives. Further ablation study also confirms the validity of each design choice.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 514-523
BOMGraph: Boosting Multi-scenario E-commerce Search with a Unified Graph Neural Network
Mobile Taobao Application delivers search services on multiple scenarios that take textual, visual, or product queries. This paper aims to propose a unified graph neural network for these search scenarios to leverage data from multiple scenarios and jointly optimize search performances with less training and maintenance costs. Towards this end, this paper proposes BOMGraph, BOosting Multi-scenario E-commerce Search with a unified Graph neural network. BOMGraph is embodied with several components to address challenges in multi-scenario search. It captures heterogeneous information flow across scenarios by inter-scenario and intra-scenario metapaths. It learns robust item representations by disentangling specific characteristics for different scenarios and encoding common knowledge across scenarios. It alleviates label scarcity and long-tail problems in scenarios with low traffic by contrastive learning with cross-scenario augmentation. BOMGraph has been deployed in production by Alibaba's E-commerce search advertising platform. Both offline evaluations and online A/B tests demonstrate the effectiveness of BOMGraph.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 514-523
Open AccessBOMGraph: Boosting Multi-scenario E-commerce Search with a Unified Graph Neural Network
Mobile Taobao Application delivers search services on multiple scenarios that take textual, visual, or product queries. This paper aims to propose a unified graph neural network for these search scenarios to leverage data from multiple scenarios and jointly optimize search performances with less training and maintenance costs. Towards this end, this paper proposes BOMGraph, BOosting Multi-scenario E-commerce Search with a unified Graph neural network. BOMGraph is embodied with several components to address challenges in multi-scenario search. It captures heterogeneous information flow across scenarios by inter-scenario and intra-scenario metapaths. It learns robust item representations by disentangling specific characteristics for different scenarios and encoding common knowledge across scenarios. It alleviates label scarcity and long-tail problems in scenarios with low traffic by contrastive learning with cross-scenario augmentation. BOMGraph has been deployed in production by Alibaba's E-commerce search advertising platform. Both offline evaluations and online A/B tests demonstrate the effectiveness of BOMGraph.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 4813-4822
Joint Optimization of Ranking and Calibration with Contextualized Hybrid Model
Despite the development of ranking optimization techniques, pointwise loss remains the dominating approach for click-through rate prediction. It can be attributed to the calibration ability of the pointwise loss since the prediction can be viewed as the click probability. In practice, a CTR prediction model is also commonly assessed with the ranking ability. To optimize the ranking ability, ranking loss (e.g., pairwise or listwise loss) can be adopted as they usually achieve better rankings than pointwise loss. Previous studies have experimented with a direct combination of the two losses to obtain the benefit from both losses and observed an improved performance. However, previous studies break the meaning of output logit as the click-through rate, which may lead to sub-optimal solutions. To address this issue, we propose an approach that can Jointly optimize the Ranking and Calibration abilities (JRC for short). JRC improves the ranking ability by contrasting the logit value for the sample with different labels and constrains the predicted probability to be a function of the logit subtraction. We further show that JRC consolidates the interpretation of logits, where the logits model the joint distribution. With such an interpretation, we prove that JRC approximately optimizes the contextualized hybrid discriminative-generative objective. Experiments on public and industrial datasets and online A/B testing show that our approach improves both ranking and calibration abilities. Since May 2022, JRC has been deployed on the display advertising platform of Alibaba and has obtained significant performance improvements.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 4813-4822
Open AccessJoint Optimization of Ranking and Calibration with Contextualized Hybrid Model
Despite the development of ranking optimization techniques, pointwise loss remains the dominating approach for click-through rate prediction. It can be attributed to the calibration ability of the pointwise loss since the prediction can be viewed as the click probability. In practice, a CTR prediction model is also commonly assessed with the ranking ability. To optimize the ranking ability, ranking loss (e.g., pairwise or listwise loss) can be adopted as they usually achieve better rankings than pointwise loss. Previous studies have experimented with a direct combination of the two losses to obtain the benefit from both losses and observed an improved performance. However, previous studies break the meaning of output logit as the click-through rate, which may lead to sub-optimal solutions. To address this issue, we propose an approach that can Jointly optimize the Ranking and Calibration abilities (JRC for short). JRC improves the ranking ability by contrasting the logit value for the sample with different labels and constrains the predicted probability to be a function of the logit subtraction. We further show that JRC consolidates the interpretation of logits, where the logits model the joint distribution. With such an interpretation, we prove that JRC approximately optimizes the contextualized hybrid discriminative-generative objective. Experiments on public and industrial datasets and online A/B testing show that our approach improves both ranking and calibration abilities. Since May 2022, JRC has been deployed on the display advertising platform of Alibaba and has obtained significant performance improvements.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2885-2897
E-commerce Search via Content Collaborative Graph Neural Network
Recently, many E-commerce search models are based on Graph Neural Networks (GNNs). Despite their promising performances, they are (1) lacking proper semantic representation of product contents; (2) less efficient for industry-scale graphs; and (3) less accurate on long-tail queries and cold-start products. To address these problems simultaneously, this paper proposes CC-GNN, a novel Content Collaborative Graph Neural Network. Firstly, CC-GNN enables content phrases to participate explicitly in graph propagation to capture the proper meaning of phrases and semantic drifts. Secondly, CC-GNN presents several efforts towards a more scalable graph learning framework, including efficient graph construction, MetaPath-guided Message Passing, and Difficulty-aware Representation Perturbation for graph contrastive learning. Furthermore, CC-GNN adopts Counterfactual Data Supplement at both supervised and contrastive learning to resolve the long-tail/cold-start problems. Extensive experiments on a real E-commerce dataset of 100-million-scale nodes show that CC-GNN produces significant improvements over existing methods (i.e., more than 10% improvements in terms of several key evaluation metrics for overall, long-tail queries and cold-start products) while reducing computational complexity. The proposed components of CC-GNN can be applied to other models for search and recommendation tasks. Experiments on a public dataset show that applying the proposed components can improve the performance of different recommendation models.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2885-2897
Open AccessE-commerce Search via Content Collaborative Graph Neural Network
Recently, many E-commerce search models are based on Graph Neural Networks (GNNs). Despite their promising performances, they are (1) lacking proper semantic representation of product contents; (2) less efficient for industry-scale graphs; and (3) less accurate on long-tail queries and cold-start products. To address these problems simultaneously, this paper proposes CC-GNN, a novel Content Collaborative Graph Neural Network. Firstly, CC-GNN enables content phrases to participate explicitly in graph propagation to capture the proper meaning of phrases and semantic drifts. Secondly, CC-GNN presents several efforts towards a more scalable graph learning framework, including efficient graph construction, MetaPath-guided Message Passing, and Difficulty-aware Representation Perturbation for graph contrastive learning. Furthermore, CC-GNN adopts Counterfactual Data Supplement at both supervised and contrastive learning to resolve the long-tail/cold-start problems. Extensive experiments on a real E-commerce dataset of 100-million-scale nodes show that CC-GNN produces significant improvements over existing methods (i.e., more than 10% improvements in terms of several key evaluation metrics for overall, long-tail queries and cold-start products) while reducing computational complexity. The proposed components of CC-GNN can be applied to other models for search and recommendation tasks. Experiments on a public dataset show that applying the proposed components can improve the performance of different recommendation models.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 517-526
Multi-Scenario Ranking with Adaptive Feature Learning
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 517-526
Open AccessMulti-Scenario Ranking with Adaptive Feature Learning
- Open Access
- 14 August 2022
- Published by Association for Computing Machinery (ACM)
- p. 2732-2740
EXTR: Click-Through Rate Prediction with Externalities in E-Commerce Sponsored Search
Click-Through Rate (CTR) prediction, estimating the probability of a user clicking on items, plays a key fundamental role in sponsored search. E-commerce platforms display organic search results and advertisements (ads), collectively called items, together as a mixed list. The items displayed around the predicted ad, i.e. external items, may affect the user clicking on the predicted. Previous CTR models assume the user click only relies on the ad itself, which overlooks the effects of external items, referred to as external effects, or externalities. During the advertising prediction, the organic results have been generated by the organic system, while the final displayed ads on multiple ad slots have not been figured out, which leads to two challenges: 1) the predicted (target) ad may win any ad slot, bringing about diverse externalities. 2) external ads are undetermined, resulting in incomplete externalities. Facing the above challenges, inspired by the Transformer, we propose EXternality TRansformer (EXTR) which regards target ad with all slots as query and external items as key&value to model externalities in all exposure situations in parallel. Furthermore, we design a Potential Allocation Generator (PAG) for EXTR, to learn the allocation of potential external ads to complete the externalities. Extensive experimental results on Alibaba datasets demonstrate the effectiveness of externalities in the task of CTR prediction and illustrate that our proposed approach can bring significant profits to the real-world e-commerce platform. EXTR now has been successfully deployed in the online search advertising system in Alibaba, serving the main traffic.
- 14 August 2022
- Published by Association for Computing Machinery (ACM)
- p. 2732-2740
Open AccessEXTR: Click-Through Rate Prediction with Externalities in E-Commerce Sponsored Search
Click-Through Rate (CTR) prediction, estimating the probability of a user clicking on items, plays a key fundamental role in sponsored search. E-commerce platforms display organic search results and advertisements (ads), collectively called items, together as a mixed list. The items displayed around the predicted ad, i.e. external items, may affect the user clicking on the predicted. Previous CTR models assume the user click only relies on the ad itself, which overlooks the effects of external items, referred to as external effects, or externalities. During the advertising prediction, the organic results have been generated by the organic system, while the final displayed ads on multiple ad slots have not been figured out, which leads to two challenges: 1) the predicted (target) ad may win any ad slot, bringing about diverse externalities. 2) external ads are undetermined, resulting in incomplete externalities. Facing the above challenges, inspired by the Transformer, we propose EXternality TRansformer (EXTR) which regards target ad with all slots as query and external items as key&value to model externalities in all exposure situations in parallel. Furthermore, we design a Potential Allocation Generator (PAG) for EXTR, to learn the allocation of potential external ads to complete the externalities. Extensive experimental results on Alibaba datasets demonstrate the effectiveness of externalities in the task of CTR prediction and illustrate that our proposed approach can bring significant profits to the real-world e-commerce platform. EXTR now has been successfully deployed in the online search advertising system in Alibaba, serving the main traffic.