Sheng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sheng Chen has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Jinpeng Wang
Meituan, Beijing, China
5 shared publications - Wayne Xin Zhao
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
4 shared publications - Ji-Rong Wen
Gaoling School of Artificial Intelligence, Renmin University of China, China
3 shared publications - Lanling Xu
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
3 shared publications - Bingqian Li
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
2 shared publications - Junjie Zhang
ByteDance Search, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 28 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (6) , 1-28
Dual-Stream MLP is All You Need for CTR Prediction
Click-through rate (CTR) prediction holds a pivotal role in online advertising and recommendation systems, where even small improvements can significantly boost revenue. Existing research primarily focuses on designing dual-stream architectures to capture effective complex feature interactions from both explicit and implicit perspectives. However, these approaches are faced with two major challenges: 1) the high complexity of feature interaction learning, which increases computational demands and the overfitting risk, and 2) the imbalance between explicit and implicit modules, where one module’s output may dominate the final prediction. To address these issues, in this paper, we propose D ual- S tream MLP ( DS-MLP ), a novel feature interaction framework for the CTR prediction task. Specially, it leverages knowledge distillation to consolidate the capacity of learning explicit feature interaction into a main MLP network, while a parallel MLP simultaneously captures implicit feature interactions as a complement. To effectively optimize the dual-stream MLP architecture, we further design a specific learning approach with two alignment strategies for enhancing the compatibility of the two MLP components. Experiments demonstrate that DS-MLP , though merely a vanilla MLP structure (the final model), can achieve state-of-the-art performance across three widely used benchmarks, offering a scalable and efficient solution for large-scale recommendation systems. Our code is available at https://github.com/RUCAIBox/DS-MLP .
- 28 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (6) , 1-28
Open AccessDual-Stream MLP is All You Need for CTR Prediction
Click-through rate (CTR) prediction holds a pivotal role in online advertising and recommendation systems, where even small improvements can significantly boost revenue. Existing research primarily focuses on designing dual-stream architectures to capture effective complex feature interactions from both explicit and implicit perspectives. However, these approaches are faced with two major challenges: 1) the high complexity of feature interaction learning, which increases computational demands and the overfitting risk, and 2) the imbalance between explicit and implicit modules, where one module’s output may dominate the final prediction. To address these issues, in this paper, we propose D ual- S tream MLP ( DS-MLP ), a novel feature interaction framework for the CTR prediction task. Specially, it leverages knowledge distillation to consolidate the capacity of learning explicit feature interaction into a main MLP network, while a parallel MLP simultaneously captures implicit feature interactions as a complement. To effectively optimize the dual-stream MLP architecture, we further design a specific learning approach with two alignment strategies for enhancing the compatibility of the two MLP components. Experiments demonstrate that DS-MLP , though merely a vanilla MLP structure (the final model), can achieve state-of-the-art performance across three widely used benchmarks, offering a scalable and efficient solution for large-scale recommendation systems. Our code is available at https://github.com/RUCAIBox/DS-MLP .
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 771-780
Twin-Flow Generative Ranking Network for Recommendation
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 771-780
Open AccessTwin-Flow Generative Ranking Network for Recommendation
- Open Access
- 6 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (5) , 1-51
Tapping the Potential of Large Language Models as Recommender Systems: A Comprehensive Framework and Empirical Analysis
Recently, Large Language Models (LLMs) such as ChatGPT have showcased remarkable abilities in solving general tasks, demonstrating the potential for applications in recommender systems. To assess how effectively LLMs can be used in recommendation tasks, our study primarily focuses on employing LLMs as recommender systems through prompt engineering. We propose a general framework for leveraging LLMs in recommendation tasks, focusing on the capabilities of LLMs as recommenders. To conduct our analysis, we formalize the input of LLMs for recommendation into natural language prompts with two key aspects and explain how our framework can be generalized to various recommendation scenarios. As for the use of LLMs as recommenders, we analyze the impact of public availability, tuning strategies, model architecture, parameter scale, and context length on recommendation results based on the classification of LLMs. As for prompt engineering, we further analyze the impact of four important components of prompts, i.e., task descriptions, user interest modeling, candidate items construction, and prompting strategies. In each section, we first define and categorize concepts in line with the existing literature. Then, we propose inspiring research questions followed by detailed experiments on two public datasets, in order to systematically analyze the impact of different factors on recommendation performance. Based on our empirical analysis, we finally summarize promising directions to shed lights on future research.
- 6 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (5) , 1-51
Open AccessTapping the Potential of Large Language Models as Recommender Systems: A Comprehensive Framework and Empirical Analysis
Recently, Large Language Models (LLMs) such as ChatGPT have showcased remarkable abilities in solving general tasks, demonstrating the potential for applications in recommender systems. To assess how effectively LLMs can be used in recommendation tasks, our study primarily focuses on employing LLMs as recommender systems through prompt engineering. We propose a general framework for leveraging LLMs in recommendation tasks, focusing on the capabilities of LLMs as recommenders. To conduct our analysis, we formalize the input of LLMs for recommendation into natural language prompts with two key aspects and explain how our framework can be generalized to various recommendation scenarios. As for the use of LLMs as recommenders, we analyze the impact of public availability, tuning strategies, model architecture, parameter scale, and context length on recommendation results based on the classification of LLMs. As for prompt engineering, we further analyze the impact of four important components of prompts, i.e., task descriptions, user interest modeling, candidate items construction, and prompting strategies. In each section, we first define and categorize concepts in line with the existing literature. Then, we propose inspiring research questions followed by detailed experiments on two public datasets, in order to systematically analyze the impact of different factors on recommendation performance. Based on our empirical analysis, we finally summarize promising directions to shed lights on future research.
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4563-4570
EXIT: An EXplicit Interest Transfer Framework for Cross-Domain Recommendation
Cross-domain recommendation has attracted substantial interest in industrial apps such as Meituan, which serves multiple business domains via knowledge transfer and meets the diverse interests of users. However, existing methods typically follow an implicit modeling paradigm that blends the knowledge from both the source and target domains, and design intricate network structures to share learned embeddings or patterns between domains to improve recommendation accuracy. Since the transfer of interest signals is unsupervised, these implicit paradigms often struggle with the negative transfer resulting from differences in service functions and presentation forms across different domains. In this paper, we propose a simple and effective EXplicit Interest Transfer framework named EXIT to address the stated challenge. Specifically, we propose a novel label combination approach that enables the model to directly learn beneficial source domain interests through supervised learning, while excluding inappropriate interest signals. Moreover, we introduce a scene selector network to model the interest transfer intensity under fine-grained scenes. Offline experiments conducted on the industrial production dataset and online A/B tests validate the superiority and effectiveness of our proposed framework. Without complex network structures or training processes, EXIT can be easily deployed in the industrial recommendation system. EXIT has been successfully deployed in the online homepage recommendation system of Meituan App, serving the main traffic.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4563-4570
Open AccessEXIT: An EXplicit Interest Transfer Framework for Cross-Domain Recommendation
Cross-domain recommendation has attracted substantial interest in industrial apps such as Meituan, which serves multiple business domains via knowledge transfer and meets the diverse interests of users. However, existing methods typically follow an implicit modeling paradigm that blends the knowledge from both the source and target domains, and design intricate network structures to share learned embeddings or patterns between domains to improve recommendation accuracy. Since the transfer of interest signals is unsupervised, these implicit paradigms often struggle with the negative transfer resulting from differences in service functions and presentation forms across different domains. In this paper, we propose a simple and effective EXplicit Interest Transfer framework named EXIT to address the stated challenge. Specifically, we propose a novel label combination approach that enables the model to directly learn beneficial source domain interests through supervised learning, while excluding inappropriate interest signals. Moreover, we introduce a scene selector network to model the interest transfer intensity under fine-grained scenes. Offline experiments conducted on the industrial production dataset and online A/B tests validate the superiority and effectiveness of our proposed framework. Without complex network structures or training processes, EXIT can be easily deployed in the industrial recommendation system. EXIT has been successfully deployed in the online homepage recommendation system of Meituan App, serving the main traffic.
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5015-5022
Sequence-level Semantic Representation Fusion for Recommender Systems
With the rapid development of recommender systems, there is increasing side information that can be employed to improve the recommendation performance. Specially, we focus on the utilization of the associated textual data of items (e.g., product title) and study how text features can be effectively fused with ID features in sequential recommendation. In this paper, we propose a novel Te xt-I D semantic fusion approach for sequential Rec ommendation, namely TedRec. The core idea is to conduct a sequence-level semantic fusion approach by integrating global contexts. The key strategy lies in that we transform the text and ID embeddings by Fourier Transform from time domain to frequency domain. In the frequency domain, the global sequential characteristics of the original sequences are inherently aggregated into the transformed representations, so that we can employ simple multiplicative operations to effectively fuse the two kinds of item features. Our fusion approach can be proved to have the same effects of contextual convolution, so as to achieving sequence-level semantic fusion. Further, we propose to enhance the discriminability of the text embeddings from the text encoder, by adaptively injecting positional information via a mixture-of-experts (MoE) modulation method. Both offline and online experiments demonstrate the effectiveness of our approach.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5015-5022
Open AccessSequence-level Semantic Representation Fusion for Recommender Systems
With the rapid development of recommender systems, there is increasing side information that can be employed to improve the recommendation performance. Specially, we focus on the utilization of the associated textual data of items (e.g., product title) and study how text features can be effectively fused with ID features in sequential recommendation. In this paper, we propose a novel Te xt-I D semantic fusion approach for sequential Rec ommendation, namely TedRec. The core idea is to conduct a sequence-level semantic fusion approach by integrating global contexts. The key strategy lies in that we transform the text and ID embeddings by Fourier Transform from time domain to frequency domain. In the frequency domain, the global sequential characteristics of the original sequences are inherently aggregated into the transformed representations, so that we can employ simple multiplicative operations to effectively fuse the two kinds of item features. Our fusion approach can be proved to have the same effects of contextual convolution, so as to achieving sequence-level semantic fusion. Further, we propose to enhance the discriminability of the text embeddings from the text encoder, by adaptively injecting positional information via a mixture-of-experts (MoE) modulation method. Both offline and online experiments demonstrate the effectiveness of our approach.
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 918-923
Promoting Two-sided Fairness with Adaptive Weights for Providers and Customers in Recommendation
At present, most recommender systems involve two stakeholders, providers and customers. Apart from maximizing the recommendation accuracy, the fairness issue for both sides should also be considered. Most of previous studies try to improve two-sided fairness with post-processing algorithms or fairness-aware loss constraints, which are highly dependent on the heuristic adjustments without respect to the optimization goal of accuracy. In contrast, we propose a novel training framework, adaptive weighting towards two-sided fairness-aware recommendation (named Ada2Fair), which lies in the extension of the accuracy-focused objective to a controllable preference learning loss over the interaction data. Specifically, we adjust the optimization scale of an interaction sample with an adaptive weight generator, and estimate the two-sided fairness-aware weights within model training. During the training process, the recommender is trained with two-sided fairness-aware weights to boost the utility of niche providers and inactive customers in a unified way. Extensive experiments on three public datasets verify the effectiveness of Ada2Fair, which can achieve Pareto efficiency in two-sided fairness-aware recommendation.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 918-923
Open AccessPromoting Two-sided Fairness with Adaptive Weights for Providers and Customers in Recommendation
At present, most recommender systems involve two stakeholders, providers and customers. Apart from maximizing the recommendation accuracy, the fairness issue for both sides should also be considered. Most of previous studies try to improve two-sided fairness with post-processing algorithms or fairness-aware loss constraints, which are highly dependent on the heuristic adjustments without respect to the optimization goal of accuracy. In contrast, we propose a novel training framework, adaptive weighting towards two-sided fairness-aware recommendation (named Ada2Fair), which lies in the extension of the accuracy-focused objective to a controllable preference learning loss over the interaction data. Specifically, we adjust the optimization scale of an interaction sample with an adaptive weight generator, and estimate the two-sided fairness-aware weights within model training. During the training process, the recommender is trained with two-sided fairness-aware weights to boost the utility of niche providers and inactive customers in a unified way. Extensive experiments on three public datasets verify the effectiveness of Ada2Fair, which can achieve Pareto efficiency in two-sided fairness-aware recommendation.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4923-4929
SPM: Structured Pretraining and Matching Architectures for Relevance Modeling in Meituan Search
In e-commerce search, relevance between query and documents is an essential requirement for satisfying user experience. Different from traditional e-commerce platforms that offer products, users search on life service platforms such as Meituan mainly for product providers, which usually have abundant structured information, e.g. name, address, category, thousands of products. Modeling search relevance with these rich structured contents is challenging due to the following issues: (1) there is language distribution discrepancy among different fields of structured document, making it difficult to directly adopt off-the-shelf pretrained language model based methods like BERT. (2) different fields usually have different importance and their length vary greatly, making it difficult to extract document information helpful for relevance matching. To tackle these issues, in this paper we propose a novel two-stage pretraining and matching architecture for relevance matching with rich structured documents. At pretraining stage, we propose an effective pretraining method that employs both query and multiple fields of document as inputs, including an effective information compression method for lengthy fields. At relevance matching stage, a novel matching method is proposed by leveraging domain knowledge in search query to generate more effective document representations for relevance scoring. Extensive offline experiments and online A/B tests on millions of users verify that the proposed architectures effectively improve the performance of relevance modeling. The model has already been deployed online, serving the search traffic of Meituan for over a year.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4923-4929
Open AccessSPM: Structured Pretraining and Matching Architectures for Relevance Modeling in Meituan Search
In e-commerce search, relevance between query and documents is an essential requirement for satisfying user experience. Different from traditional e-commerce platforms that offer products, users search on life service platforms such as Meituan mainly for product providers, which usually have abundant structured information, e.g. name, address, category, thousands of products. Modeling search relevance with these rich structured contents is challenging due to the following issues: (1) there is language distribution discrepancy among different fields of structured document, making it difficult to directly adopt off-the-shelf pretrained language model based methods like BERT. (2) different fields usually have different importance and their length vary greatly, making it difficult to extract document information helpful for relevance matching. To tackle these issues, in this paper we propose a novel two-stage pretraining and matching architecture for relevance matching with rich structured documents. At pretraining stage, we propose an effective pretraining method that employs both query and multiple fields of document as inputs, including an effective information compression method for lengthy fields. At relevance matching stage, a novel matching method is proposed by leveraging domain knowledge in search query to generate more effective document representations for relevance scoring. Extensive offline experiments and online A/B tests on millions of users verify that the proposed architectures effectively improve the performance of relevance modeling. The model has already been deployed online, serving the search traffic of Meituan for over a year.