Main picture

Ph.D. Candidate

Department of Computing (COMP)
The Hong Kong Polytechnic University (PolyU)
Supervisor: Dr. Fan Wenqi
Co-supervisor: Prof. Li Qing

Email: shijie.wang(at)connect.polyu.hk
Office: VA324, Kowloon, Hong Kong SAR

Google Scholar   GitHub   Linkedin

Bio

I am a third-year PhD Candidate in the department of Computing of The Hong Kong Polytechnic University (PolyU), advised by Assistant Professor Fan Wenqi and Prof. Li Qing. My current research focuses on Large Language Models (LLMs) and Graph Neural Networks (GNNs) as well as their applications in recommender systems (RecSys).

I obtained my BSc degree in Information and Computing Science from Xi’an Jiaotong-Liverpool University in China and the University of Liverpool in the UK in July, 2022.

News

 

Selected Publications

For a full list of publications, see Research. * indicates equal contribution.
,
Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation
In Preprint, 2025.
Recently, Retrieval-Augmented Generation (RAG) has garnered significant attention for addressing these limitations by leveraging external knowledge sources to enhance the understanding and generation of LLMs. However, vanilla RAG methods often introduce noise and neglect structural relationships in knowledge, limiting their effectiveness in LLM-based recommendations. To address these limitations, we propose to retrieve high-quality and up-to-date structure information from the knowledge graph (KG) to augment recommendations. Specifically, our approach develops a retrieval-augmented framework, termed K-RagRec, that facilitates the recommendation generation process by incorporating structure information from the external KG. Extensive experiments have been conducted to demonstrate the effectiveness of our proposed method.
paper
,
Score-based Generative Diffusion Models for Social Recommendations
In Preprint, 2024.
In this paper, we tackle the low social homophily challenge from an innovative generative perspective, directly generating optimal user social representations that maximize consistency with collaborative signals. Specifically, we propose the Score-based Generative Model for Social Recommendation (SGSR), which effectively adapts the Stochastic Differential Equation (SDE)-based diffusion models for social recommendations. To better fit the recommendation context, SGSR employs a joint curriculum training strategy to mitigate challenges related to missing supervision signals and leverages self-supervised learning techniques to align knowledge across social and collaborative domains. Extensive experiments on real-world datasets demonstrate the effectiveness of our approach in filtering redundant social information and improving recommendation performance.
paper
,
Multi-agent Attacks for Black-box Social Recommendations
In Transactions on Information Systems (TOIS), 2024.
To perform untargeted attacks on social recommender systems, attackers can construct malicious social relationships for fake users to enhance the attack performance. However, the coordination of social relations and item profiles is challenging for attacking black-box social recommendations. To address this limitation, we first conduct several preliminary studies to demonstrate the effectiveness of cross-community connections and cold-start items in degrading recommendations performance. Specifically, we propose a novel framework Multiattack based on multi-agent reinforcement learning to coordinate the generation of cold-start item profiles and cross-community social relations for conducting untargeted attacks on black-box social recommendations. Comprehensive experiments on various real-world datasets demonstrate the effectiveness of our proposed attacking framework under the black-box setting.
paper
, ,
CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
In KDD, 2024.
In this paper, we propose a novel attack framework called CheatAgent by harnessing the human-like capabilities of LLMs, where an LLM-based agent is developed to attack LLM-Empowered RecSys. Specifically, our method first identifies the insertion position for maximum impact with minimal input modification. After that, the LLM agent is designed to generate adversarial perturbations to insert at target positions. To further improve the quality of generated perturbations, we utilize the prompt tuning technique to improve attacking strategies via feedback from the victim RecSys iteratively. Extensive experiments across three real-world datasets demonstrate the effectiveness of our proposed attacking method.
paper
, ,
A Survey on RAG Meets LLMs: Towards Retrieval-Augmented Large Language Models
In KDD, 2024.
In this survey, we comprehensively review existing research studies in retrieval-augmented large language models (RA-LLMs), covering three primary technical perspectives: architectures, training strategies, and applications. As the preliminary knowledge, we briefly introduce the foundations and recent advances of LLMs. Then, to illustrate the practical significance of RAG for LLMs, we categorize mainstream relevant work by application areas, detailing specifically the challenges of each and the corresponding capabilities of RA-LLMs. Finally, to deliver deeper insights, we discuss current limitations and several promising directions for future research.
paper
, ,
Graph Machine Learning in the Era of Large Language Models (LLMs)
In Preprint, 2024.
In this survey, we first review the recent developments in Graph ML. We then explore how LLMs can be utilized to enhance the quality of graph features, alleviate the reliance on labeled data, and address challenges such as graph heterogeneity and out-of-distribution (OOD) generalization. Afterward, we delve into how graphs can enhance LLMs, highlighting their abilities to enhance LLM pre-training and inference. Furthermore, we investigate various applications and discuss the potential future directions in this promising field.
paper
, ,
Graph Unlearning with Efficient Partial Retraining
In WWW PhD Symposium, 2024.
Graph Neural Networks (GNNs) have achieved remarkable success in various real-world applications. However, GNNs may be trained on undesirable graph data, which can degrade their performance and reliability. To enable trained GNNs to efficiently unlearn unwanted data, a desirable solution is retraining-based graph unlearning, which partitions the training graph into subgraphs and trains sub-models on them, allowing fast unlearning through partial retraining. However, the graph partition process causes information loss in the training graph, resulting in the low model utility of sub-GNN models. In this paper, we propose GraphRevoker, a novel graph unlearning framework that better maintains the model utility of unlearnable GNNs.
paper
,
A novel Multi-Agent Deep RL Approach for Traffic Signal Control
In PerCom Workshop, 2023.
As travel demand increases and urban traffic condition becomes more complicated, applying multi-agent deep reinforcement learning (MARL) to traffic signal control becomes one of the hot topics. The rise of Reinforcement Learning (RL) has opened up opportunities for solving Adaptive Traffic Signal Control (ATSC) in complex urban traffic networks, and deep neural networks have further enhanced their ability to handle complex data. Traditional research in traffic signal control is based on the centralized Reinforcement Learning technique. However, in a large-scale road network, centralized RL is infeasible because of an exponential growth of joint state-action space. In this paper, we propose a Friend-Deep Q-network (Friend-DQN) approach for multiple traffic signal control in urban networks, which is based on an agent-cooperation scheme. In particular, the cooperation between multiple agents can reduce the state-action space and thus speed up the convergence.
paper