Back to Search
Start Over
EasyDGL: Encode, Train and Interpret for Continuous-Time Dynamic Graph Learning.
- Source :
-
IEEE transactions on pattern analysis and machine intelligence [IEEE Trans Pattern Anal Mach Intell] 2024 Aug 14; Vol. PP. Date of Electronic Publication: 2024 Aug 14. - Publication Year :
- 2024
- Publisher :
- Ahead of Print
-
Abstract
- Dynamic graphs arise in various real-world applications, and it is often welcomed to model the dynamics in continuous time domain for its flexibility. This paper aims to design an easy-to-use pipeline (EasyDGL which is also due to its implementation by DGL toolkit) composed of three modules with both strong fitting ability and interpretability, namely encoding, training and interpreting: i) a temporal point process (TPP) modulated attention architecture to endow the continuous-time resolution with the coupled spatiotemporal dynamics of the graph with edge-addition events; ii) a principled loss composed of task-agnostic TPP posterior maximization based on observed events, and a task-aware loss with a masking strategy over dynamic graph, where the tasks include dynamic link prediction, dynamic node classification and node traffic forecasting; iii) interpretation of the outputs (e.g., representations and predictions) with scalable perturbation-based quantitative analysis in the graph Fourier domain, which could comprehensively reflect the behavior of the learned model. Empirical results on public benchmarks show our superior performance for time-conditioned predictive tasks, and in particular EasyDGL can effectively quantify the predictive power of frequency content that a model learns from evolving graph data.
Details
- Language :
- English
- ISSN :
- 1939-3539
- Volume :
- PP
- Database :
- MEDLINE
- Journal :
- IEEE transactions on pattern analysis and machine intelligence
- Publication Type :
- Academic Journal
- Accession number :
- 39141470
- Full Text :
- https://doi.org/10.1109/TPAMI.2024.3443110