Belangrijkste concepten
A novel multi-perspective feedback-attention coupling model (MPFA) that effectively learns the complex dynamics of continuous-time dynamic graphs by capturing both the evolving and original perspectives of node interactions.
Samenvatting
The paper introduces a novel model called MPFA (Multi-Perspective Feedback-Attention Coupling) for continuous-time dynamic graph representation learning. MPFA addresses several key challenges in this domain:
- Most existing methods focus on static or discrete-time dynamic graphs, while MPFA can effectively handle continuous-time dynamic graphs.
- MPFA models the dynamic graph evolution from two perspectives - the evolving perspective and the original perspective. The evolving perspective captures the current state of historical interaction events, while the original perspective retains the essence of past interactions.
- MPFA employs a temporal attention module in the evolving perspective to aggregate current state information, and a feedback attention module in the original perspective to capture the growth characteristics from original to current states.
- The two perspectives are coupled through an attention coupling module to improve the model's generalization and prediction capabilities.
- Experimental results on one self-organized dataset and seven public datasets demonstrate the effectiveness of MPFA in both dynamic link prediction and dynamic node classification tasks, outperforming state-of-the-art baselines.
Statistieken
The dynamic graph data is represented as a sequence of time-ordered interaction events between nodes.
The number of nodes ranges from 1,000 to 8,295 across the datasets.
The number of interactions ranges from 150,035 to 1,293,103 across the datasets.
Citaten
"MPFA incorporates information from both evolving and original perspectives to effectively learn the complex dynamics of dynamic graph evolution processes."
"The evolving perspective considers the current state of historical interaction events of nodes and uses a temporal attention module to aggregate current state information."
"The original perspective utilizes a feedback attention module with growth characteristic coefficients to aggregate the original state information of node interactions."