Temporal receptive field in dynamic graph learning: A comprehensive analysis
This work addresses a critical gap in dynamic graph analysis for applications like recommender systems, though it is incremental as it focuses on analysis rather than introducing new methods.
The study tackled the overlooked concept of temporal receptive field in dynamic graph learning for link prediction, finding that appropriately chosen temporal contexts can significantly enhance model performance, while overly large windows may reduce accuracy.
Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refers to the temporal context that models use for making predictions, has been largely overlooked and insufficiently analyzed in existing research. In this study, we present a comprehensive analysis of the temporal receptive field in dynamic graph learning. By examining multiple datasets and models, we formalize the role of temporal receptive field and highlight their crucial influence on predictive accuracy. Our results demonstrate that appropriately chosen temporal receptive field can significantly enhance model performance, while for some models, overly large windows may introduce noise and reduce accuracy. We conduct extensive benchmarking to validate our findings, ensuring that all experiments are fully reproducible. Code is available at https://github.com/ykrmm/BenchmarkTW .