9 citations · 20 across the 7 of their papers we have counts for
7 papers
Dynamic Heterogeneous Graph Representation Learning: A Survey
Huan Liu, Pengfei Jiao, Jie Yin +2
Graph representation learning (GRL) serves as a canonical paradigm for modeling complex networks. However, real-world AI systems inherently manifest as evolving heterogeneous entit…
TGFormer: Towards Temporal Graph Transformer with Auto-Correlation Mechanism
Hongjiang Chen, Pengfei Jiao, Ming Du +4
The growing interest in Temporal Graph Neural Networks (TGNNs) stems from their ability to model complex dynamics and deliver superior performance. However, TGNNs encounter fundame…
ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
Hongjiang Chen, Xin Zheng, Pengfei Jiao +5
Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks. However, their interpretability remains limited, as most TGNNs…
GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
Hongjiang Chen, Xin Zheng, Yixin Liu +7
Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the under…
HGMP:Heterogeneous Graph Multi-Task Prompt Learning
Pengfei Jiao, Jialong Ni, Di Jin +4
The pre-training and fine-tuning methods have gained widespread attention in the field of heterogeneous graph neural networks due to their ability to leverage large amounts of unla…
A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities
Pengfei Jiao, Hongjiang Chen, Xuan Guo +3
Temporal interaction graphs (TIGs), defined by sequences of timestamped interaction events, have become ubiquitous in real-world applications due to their capability to model compl…
Temporal Graph Representation Learning with Adaptive Augmentation Contrastive
Hongjiang Chen, Pengfei Jiao, Huijun Tang +1
Temporal graph representation learning aims to generate low-dimensional dynamic node embeddings to capture temporal information as well as structural and property information. Curr…