Xiaobao Wang

MDCD: Meta-Learning Driven Conditional Diffusion for User Cold-Start in Conversational Recommendation

The conversational recommendation system (CRS) breaks the limitations of traditional static methods, presenting a novel framework for personalized recommendations with real-time adaptability and dynamic interactions. Existing methods predominantly focus on the balance between ”exploration and exploitation (E&E)”, but t...

Unsupervised Graph-level Anomaly Detection via Multi-granular Graph Structure Learning

A Unified Prompt for Enhancing Heterogeneous Graph Pre-training via Edge-based Message Passing

HGMRP extends single-relation prompts into a composite structure that includes both relation-specific and shared components, thereby enhancing expressive capability and significantly out-performs existing heterogeneous prompt methods, validating its effectiveness and superiority.

Collateral Damage Constrained Backdoor Attacks on Graph Neural Networks

The proposed Collateral Damage Constrained Graph Backdoor Attack (CDCA) combines neighborhood-aware target node selection with a self-constrained trigger generation strategy to suppress trigger-induced propagation by enforcing prediction consistency on clean K -hop neighboring nodes.

LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks

LoSplit is proposed, the first training-time defense framework in graph that leverages this early-stage loss drift to accurately split target nodes, and dynamically selects epochs with maximal loss divergence, clusters target nodes via Gaussian Mixture Models, and applies a Decoupling-Forgetting strategy to break the a...