Yuling Wang

Yuling Wang

Auto-generated profile, based on publicly available information

Yuling Wang

School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 May 2024
Verified
Conference Paper
Open access
YWYuling Wang
Yuling Wang
CTChangxin Tian
Changxin Tian
BHBinbin Hu
Binbin Hu
YYYanhua Yu
Yanhua Yu
ZLZiqi Liu
Ziqi Liu
Xiao WangXiao Wang
Xiao Wang
Large language models (LLMs) open up new horizons for sequential recommendations, owing to their remarkable language comprehension and generation capabilities. However, there are still numerous challenges that should be addressed to successfully implement sequential recommendations empowered by LLMs. Firstly, user behavior patterns are often complex, and relying solely on one-step reasoning from LLMs may lead to incorrect or task-irrelevant responses. Secondly, the prohibitively resource requirements of LLM (e.g., ChatGPT-175B) are overwhelmingly high and impractical for real sequential recommender systems. In this paper, we propose a novel Step-by-step knowLedge dIstillation fraMework for recommendation (SLIM), paving a promising path for sequential recommenders to enjoy the exceptional reasoning capabilities of LLMs in a "slim" (i.e. resource-efficient) manner. We introduce CoT prompting based on user behavior sequences for the larger teacher model. The rationales generated by the teacher model are then utilized as labels to distill the downstream smaller student model (e.g., LLaMA2-7B). In this way, the student model acquires the step-by-step reasoning capabilities in recommendation tasks. We encode the generated rationales from the student model into a dense vector, which empowers recommendation in both ID-based and ID-agnostic scenarios. Extensive experiments demonstrate the effectiveness of SLIM over state-of-the-art baselines, and further analysis showcasing its ability to generate meaningful recommendation reasoning at affordable costs.

6 January 2025 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
PJPengfei Jiao
Pengfei Jiao
WSWeijian Song
Weijian Song
YWYuling Wang
Yuling Wang
WZWang Zhang
Wang Zhang
HCHongqian Chen
Hongqian Chen
JWJian Wu
Jian Wu
Predicting the popularity of information in social networks poses a highly challenging problem. The popularity of a message is contingent upon its diffusion process and the relationships it maintains with other cascades and is influenced by user behaviour within the social network. Effectively capturing the dynamic process of message propagation and integrating the structural features of the social network to enhance popularity prediction constitutes a pivotal challenge. To address the challenge, we propose a novel method called “Cascade Social Net” (CSN) that leverages cascade graphs and social graphs to predict cascade popularity accurately. The proposed method consists of three stages. Firstly, we construct a social graph by collecting user information and their connections. Secondly, we integrate information from social graphs, cascade graphs and inter-cascade graphs. Finally, we leverage graph neural networks to predict the popularity of cascades. To overcome the challenge of large-scale social graphs, we introduce a novel neighbour sampling technique that efficiently aggregates information from second-order neighbours. We evaluate our method on real-world datasets and compare it with state-of-the-art methods. Our results demonstrate that CSN outperforms existing methods in predicting cascade popularity.

8 October 2024
Verified
Conference Paper
Open access
ZGZirui Guo
Zirui Guo
YYYanhua Yu
Yanhua Yu
YWYuling Wang
Yuling Wang
KLKangkang Lu
Kangkang Lu
ZYZixuan Yang
Zixuan Yang
TCTat-Seng Chua
Tat-Seng Chua
In the evolving landscape of recommender systems, Graph Contrastive Learning (GCL) has become a prominent method for enhancing recommendation performance by alleviating the issue of data sparsity. However, existing GCL-based recommendations often overlook the control of shared information between the contrastive views. In this paper, we initially analyze and experimentally demonstrate these methods often lead to the issue of augmented representation collapse, where the representations between views become excessively similar, diminishing their distinctiveness. To address this issue, we propose the Information-Controllable Graph Contrastive Learning (IGCL) framework, a novel approach that focuses on optimizing the shared information between views to include as much relevant information for the recommendation task as possible while maintaining an appropriate level. In particular, we design the Collaborative Signals Enhanced Augmentation module to infuse the augmented representation with rich, task-relevant collaborative signals. Furthermore, the Information-Controllable Contrastive Learning module is designed to direct control over the magnitude of shared information between the contrastive views to avoid over-similarity. Extensive experiments on three public datasets demonstrate the effectiveness of IGCL, showcasing significant improvements in performance and the capability to alleviate augmented representation collapse.


6 November 2026
Verified
Conference Paper
Open access
SZShunhang Zheng
Shunhang Zheng
PJPengfei Jiao
Pengfei Jiao
PZPinlong Zhao
Pinlong Zhao
HYHaocheng Yang
Haocheng Yang
DZDalin Zhang
Dalin Zhang
YWYuling Wang
Yuling Wang

1 November 2026 in Information Processing & Management
Verified
Journal Article
Closed access
YRYimeng Ren
Yimeng Ren
YYYanhua Yu
Yanhua Yu
LLLizi Liao
Lizi Liao
YSYuhu Shang
Yuhu Shang
YWYuling Wang
Yuling Wang
SLShouzhi Li
Shouzhi Li