Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
24. července 2023
Řečníci
O prezentaci
Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such as high computational cost and optimization difficulty. More importantly, previous NAS methods have ignored the uniqueness of GNNs, where GNNs possess expressive power without training.With the randomly-initialized weights, we can then seek the optimal architecture parameters via the sparse coding objective and derive a novel NAS-GNNs method, namely neural architecture coding (NAC). Consequently, our NAC holds a no-update scheme on GNNs and can efficiently compute in linear time. Empirical evaluations on multiple GNN benchmark datasets demonstrate that our approach leads to state-of-the-art performance, which is up to 200× faster and 18.8% more accurate than the strong baselines.Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such as high computational cost and optimization difficulty. More importantly, previous NAS methods have ignored the uniqueness of GNNs, where GNNs possess expressive power without training.With the randomly-initialized weights, we can then seek the optimal archit…
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Robust Weak Supervision with Variational Auto-Encoders
Zhlédnout později
Scaling Vision Transformers to 22 Billion Parameters
Zhlédnout později
Margin-based sampling in high dimensions: When being active is less efficient than staying passive
Zhlédnout později
Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning Algorithms
Zhlédnout později
Xingzhuo Guo, …
Magneto: A Foundation Transformer
Zhlédnout později
Hongyu Wang, …
Optimal Arms Identification with Knapsacks
Zhlédnout později
Shaoang Li, …