Publications

Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours

Published in , 2024

This work proposed a practical approach to TGNN model comparison that compares models at the modular level with a standardized and optimized implementation framework. It further revealed interplay between modules and datasets.

PA-GNN: Parameter-Adaptive Graph Neural Networks

Published in Workshop on Dynamic Neural Networks in the 39th International Conference on Machine Learning, 2024

This paper designed a trainable node-specific aggregator that learns from node position and features to create an adaptive graph filter.

Download Paper