9 papers
Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses
Ziluowen Luo, Senzhang Wang, Chaozhuo Li +9
Modern agents increasingly rely on memories, tools, and execution logic, so their competence extends beyond model parameters. This shift exposes a limitation of conventional knowle…
NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption
Ziluowen Luo, Jun Yin, Ruochen Liu +4
Post-hoc Graph Neural Network (GNN) explainers commonly follow a Perturb-Query paradigm, inferring the importance of graph elements based on queried predictions to perturbed inputs…
Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation
Bangguo Zhu, Peng Huo, Yuanbo Zhao +3
Recently, Generative Recommenders (GRs) have emerged as a transformative recommendation paradigm by replacing traditional item IDs with semantic indices (SIDs). Owing to the except…
Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders
Jun Yin, Bangguo Zhu, Peng Huo +5
Recently, Generative Recommenders (GRs), characterized by a unified end-to-end framework, have exhibited astonishing potential in transforming the recommendation paradigm. Despite…
Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs
Hao Yan, Xuanru Wang, Jun Yin +3
Multimodal Attributed Graph Learning (MAGL) integrates intrinsic node attributes with structural topology via graph aggregation. However, as pretrained encoders evolve into Large F…
Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases
Jun Yin, Peng Huo, Bangguo Zhu +4
In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to structure the RDB as a heterogeneou…
From Token Generation to Item Ranking: Direct Generative Recommendation with Semantic IDs
Yuanbo Zhao, Ruochen Liu, Senzhang Wang +6
Generative recommendation formulates item recommendation as a token-level generation task, where Semantic IDs (SIDs) represents each item as a sequence of discrete tokens. However,…
Unleash LLMs Potential for Sequential Recommendation by Coordinating Dual Dynamic Index Mechanism
Jun Yin, Zhengxin Zeng, Mingzheng Li +13
Owing to the unprecedented capability in semantic understanding and logical reasoning, large language models (LLMs) have shown fantastic potential in developing next-generation seq…
sasdim: self-adaptive noise scaling diffusion model for spatial time series imputation
Shunyang Zhang, Senzhang Wang, Xianzhen Tan +3
Spatial time series imputation is critically important to many real applications such as intelligent transportation and air quality monitoring. Although recent transformer and diff…