Hongjian Shi — accepted AI-conference papers

2026

DGTF: Cross-Domain Decentralized Graph Learning with Topology-Aware Knowledge Fusion

Ruisheng Zheng, Mingyi Li, Xiao Zhang, Hongjian Shi, Yanjie Fu, Yuan Yuan +1

AAAI 2026technical

Cross-Domain Decentralized Graph Learning (CD-DGL) is a promising paradigm that enables efficient, privacy-preserving collaboration among multiple parties to unlock the value of cross-domain graph data. However, it faces two fundamental challenges. First, inconsistent label spaces across domains dri

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Fine-Grained Global Modeling Learning for Personalized Federated Sequential Recommender

Yicheng Di, Hongjian Shi, Ruhui Ma, Yuan Liu, Weiyu Wang

ICASSP 2025accepted

Personalized sequential recommender has become a key task in the consumer electronics domain. Existing methods for personalized sequential recommenders primarily focus on modeling user behavior and have achieved satisfactory recommender results. However, the inherent quadratic computational complexi…

Cited by 0 Source ↗Scholar ↗