8 papers · 1 filter
Residual Trajectory Distillation for Generative Retrieval
Weihao Shen, Wei Chen, Fuwei Zhang +4
Generative retrieval has emerged as a general retrieval paradigm, representing items with discrete Semantic IDs (SIDs) and retrieving them through autoregressive identifier generat…
Learning Multiresolution Relevance for Hierarchical Generative Retrieval
Weihao Shen, Wei Chen, Fuwei Zhang +4
Generative retrieval with semantic identifiers (SIDs) makes successive decisions over a document hierarchy. Relevant documents for the same query may share coarse prefixes and dive…
Requirement--Evidence Alignment for Compositional E-Commerce Queries
Weihao Shen, Wei Chen, Fuwei Zhang +6
Compositional e-commerce queries express multiple requirements that must hold jointly, yet existing rerankers collapse these constraints into aggregate relevance and often promote…
Unpaired Modality-Agnostic Generative Recommendation
Weihao Shen, Wei Chen, Fuwei Zhang +6
Generative Recommendation (GR) formulates recommendation as autoregressive generation over discrete semantic identifiers (IDs). Although recent multimodal GR methods improve semant…
SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
Wei Chen, Xingyu Guo, Shuang Li +6
Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers. Recent studie…
Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
Wei Chen, Xingyu Guo, Shuang Li +4
Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs but is challenged by complex, multi-faceted distributional shifts. Existing…
Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation
Wei Chen, Xingyu Guo, Shuang Li +7
Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One pro…
You Only Anonymize What Is Not Intent-Relevant: Suppressing Non-Intent Privacy Evidence
Weihao Shen, Yaxin Xu, Shuang Li +4
Anonymizing sensitive information in user text is essential for privacy, yet existing methods often apply uniform treatment across attributes, which can conflict with communicative…