6 citations · 10 across the 31 of their papers we have counts for
13 papers · 1 filter
FedHUR: Learning Hierarchical Utility-Guided Client Relations for Personalized Federated Recommendation
Mingzhe Han, Jiahao Liu, Dongsheng Li +5
Federated recommendation enables collaborative model training while keeping user interaction data on local clients. A central problem in federated recommendation is how to aggregat…
From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents
Jiahao Liu, Mingzhe Han, Guanming Liu +6
Personalization has traditionally depended on platform-specific user models that are optimized for prediction but remain largely inaccessible to the people they describe. As LLM-ba…
Drift-Aware Continual Tokenization for Generative Recommendation
Yuebo Feng, Jiahao Liu, Mingzhe Han +5
Generative recommendation commonly adopts a two-stage pipeline in which a learnable tokenizer maps items to discrete token sequences (i.e. identifiers) and an autoregressive genera…
RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction
Ziye Tong, Jiahao Liu, Weimin Zhang +7
Multimodal content is crucial for click-through rate (CTR) prediction. However, directly incorporating continuous embeddings from pre-trained models into CTR models yields suboptim…
Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction
Jiahao Liu, Hongji Ruan, Weimin Zhang +7
This paper explores effective numerical feature embedding for Click-Through Rate prediction in streaming environments. Conventional static binning methods rely on offline statistic…
Dynamic Feature-Embedding Communication via Codebook Distillation for Federated Recommendation
Mingzhe Han, Jiahao Liu, Dongsheng Li +6
Federated recommendation systems commonly protect user privacy by keeping user parameters on local devices, while exchanging item parameters for collaborative model training. Howev…
Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models
Jiongran Wu, Jiahao Liu, Dongsheng Li +7
Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns, making them promising candidates for sequential recommenda…
LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems
Shengkang Gu, Jiahao Liu, Dongsheng Li +7
Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies of…
FedCIA: Federated Collaborative Information Aggregation for Privacy-Preserving Recommendation
Mingzhe Han, Dongsheng Li, Jiafeng Xia +5
Recommendation algorithms rely on user historical interactions to deliver personalized suggestions, which raises significant privacy concerns. Federated recommendation algorithms t…
Improving LLM-powered Recommendations with Personalized Information
Jiahao Liu, Xueshuo Yan, Dongsheng Li +6
Due to the lack of explicit reasoning modeling, existing LLM-powered recommendations fail to leverage LLMs' reasoning capabilities effectively. In this paper, we propose a pipeline…
AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations
Jiahao Liu, Shengkang Gu, Dongsheng Li +7
LLM-based user agents, which simulate user interaction behavior, are emerging as a promising approach to enhancing recommender systems. In real-world scenarios, users' interactions…
Unbiased Collaborative Filtering with Fair Sampling
Jiahao Liu, Dongsheng Li, Hansu Gu +4
Recommender systems leverage extensive user interaction data to model preferences; however, directly modeling these data may introduce biases that disproportionately favor popular…
Oracle-guided Dynamic User Preference Modeling for Sequential Recommendation
Jiafeng Xia, Dongsheng Li, Hansu Gu +4
Sequential recommendation methods can capture dynamic user preferences from user historical interactions to achieve better performance. However, most existing methods only use past…