Yuhan Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuhan Yang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Jie Zou
University of Electronic Science and Technology of China, Chengdu, China
5 shared publications - Guojia An
University of Electronic Science and Technology of China, Chengdu, Sichuan, China
4 shared publications - Yang Yang
University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Mingshi Yan
College of Intelligence and Computing, Tianjin University, Tianjin, China
2 shared publications - Fuming Sun
School of Information and Communication Engineering, Dalian Minzu University, Dalian, China
1 shared publication - Guicheng Tian1 shared publication
Latest Publications
- 28 July 2026
- Published by Elsevier in Information Processing & Management
- Vol. 64 (1)
ED4SBR: Diffusion-driven diversity enhancement for session-based recommendation
- 28 July 2026
- Published by Elsevier in Information Processing & Management
- Vol. 64 (1)
ED4SBR: Diffusion-driven diversity enhancement for session-based recommendation
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 41-52
Beyond the Single Path: Divergent Reasoning for LLM-based Recommendation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 41-52
Open AccessBeyond the Single Path: Divergent Reasoning for LLM-based Recommendation
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1787-1796
Unleashing the Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1787-1796
Open AccessUnleashing the Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5843-5852
Not All Information Brings Benefits: Personalization-Driven Agent Debate for Conversational Recommendation
Conversational recommender systems (CRSs) aim to provide real-time recommendations through dynamic interactions between users and the system. Recent studies have revealed the value of personalized information derived from users' historical dialogue records in refining user preferences. However, existing methods often utilize the entire historical dialogue of a user indiscriminately, leading to the issue of cognitive negative transfer, wherein historical dialogue sessions impede rather than facilitate current decision-making. This ultimately degrades the performance of conversational recommendations. To address this issue, inspired by the behavioral decision theory, this paper proposes a novel model, Personalization-Driven Agent Debate for Conversational Recommendation, named EyeCRS. EyeCRS is comprised of two core components: (i) The Multi-Agent Debate Module employs supporting and opposing agents to simulate a human-like debate process, thereby enabling a rigorous evaluation of whether historical dialogue sessions may introduce cognitive negative transfer into the recommender. (ii) The Parametric Injection Module, subsequently, parameterizes the historical dialogues that are validated as positive and injects them into the intrinsic parameter space of the downstream recommender, thereby effectively enhancing the model's ability to internalize and utilize personalized knowledge. Experimental results on two real-world datasets show that EyeCRS effectively mitigates cognitive negative transfer and achieves superior performance in conversational recommendation.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5843-5852
Open AccessNot All Information Brings Benefits: Personalization-Driven Agent Debate for Conversational Recommendation
Conversational recommender systems (CRSs) aim to provide real-time recommendations through dynamic interactions between users and the system. Recent studies have revealed the value of personalized information derived from users' historical dialogue records in refining user preferences. However, existing methods often utilize the entire historical dialogue of a user indiscriminately, leading to the issue of cognitive negative transfer, wherein historical dialogue sessions impede rather than facilitate current decision-making. This ultimately degrades the performance of conversational recommendations. To address this issue, inspired by the behavioral decision theory, this paper proposes a novel model, Personalization-Driven Agent Debate for Conversational Recommendation, named EyeCRS. EyeCRS is comprised of two core components: (i) The Multi-Agent Debate Module employs supporting and opposing agents to simulate a human-like debate process, thereby enabling a rigorous evaluation of whether historical dialogue sessions may introduce cognitive negative transfer into the recommender. (ii) The Parametric Injection Module, subsequently, parameterizes the historical dialogues that are validated as positive and injects them into the intrinsic parameter space of the downstream recommender, thereby effectively enhancing the model's ability to internalize and utilize personalized knowledge. Experimental results on two real-world datasets show that EyeCRS effectively mitigates cognitive negative transfer and achieves superior performance in conversational recommendation.
- 13 January 2026
- Published by Elsevier in Information Processing & Management
- Vol. 63 (4)
CooSBR: Rethinking neighborhood integration for session-based recommendation
- 13 January 2026
- Published by Elsevier in Information Processing & Management
- Vol. 63 (4)
CooSBR: Rethinking neighborhood integration for session-based recommendation