papers

Publications (7)

cs.LG2025

Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning

Jinchuan Zhang, Ming Sun, Chong Mu +3

Temporal Knowledge Graph (TKG) reasoning focuses on predicting events through historical information within snapshots distributed on a timeline. Existing studies mainly concentrate…

cs.LG2026

MA-DAR: Manifold-Aligned Dynamic Adaptive Routing for Continual Temporal Knowledge Graph Reasoning

Xiangjun Shi, Chong Mu, Jinchuan Zhang +3

Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge. Replay-based continual lear…

cs.AI2024

Learning Multi-graph Structure for Temporal Knowledge Graph Reasoning

Jinchuan Zhang, Bei Hui, Chong Mu +1

Temporal Knowledge Graph (TKG) reasoning that forecasts future events based on historical snapshots distributed over timestamps is denoted as extrapolation and has gained significa…

cs.LG2024

Learning Granularity Representation for Temporal Knowledge Graph Completion

Jinchuan Zhang, Tianqi Wan, Chong Mu +2

Temporal Knowledge Graphs (TKGs) incorporate temporal information to reflect the dynamic structural knowledge and evolutionary patterns of real-world facts. Nevertheless, TKGs are…

cs.LG2026

FedWeave: Rethinking the Unit of Specialization in Heterogeneous Federated MoE-LoRA

Donghang Duan, Xu Zheng, Lizong Zhang +2

The paper introduces FedWeave, a federated learning framework that separates expert aggregation from router optimization to better handle heterogeneous tasks by using prototype-lev…

#federated learning#parameter-efficient fine-tuning#mixture of experts#heterogeneous tasks
cs.CV2026

SAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction

Quanjiang Guo, Chong Mu, Jiazhou Pan +4

Multimodal Information Extraction (MIE)-covering tasks such as Multimodal Named Entity Recognition (MNER), Relation Extraction (MRE), and Event Extraction (MEE)-is essential for un…