Our key findings:
- Graph ML models can be generalizable yet powerful at the same time
- We offer insights to enhance a model's generalization pre-training
- Findings extend to non-graph ML models as well
Our key findings:
- Graph ML models can be generalizable yet powerful at the same time
- We offer insights to enhance a model's generalization pre-training
- Findings extend to non-graph ML models as well
Could you please add me? Thx
our paper, βTowards Bridging Generalization and Expressivity of Graph Neural Networksβ, will be presented at ICLR 2025 in Singapore this week!
We delve into the connection between expressiveness and generalization of GNNs
π Friday, 25 April
π 10:00 am β 12:30 pm SGT
π’ Hall 3 + Hall 2B
#iclr2025