Learning theory can (sometimes) explain generalisation in graph neural networks

P Esser, L Chennuru Vankadara… - Advances in Neural …, 2021 - proceedings.neurips.cc
In recent years, several results in the supervised learning setting suggested that classical
statistical learning-theoretic measures, such as VC dimension, do not adequately explain …
被引用次数：35 相关文章

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks

P Esser, D Ghoshdastidar, LC Vankadara - openreview.net
In recent years, several results in the supervised learning setting suggested that classical
statistical learning-theoretic measures, such as VC dimension, do not adequately explain …

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks

PM Esser, LC Vankadara, D Ghoshdastidar - arXiv preprint arXiv …, 2021 - arxiv.org
In recent years, several results in the supervised learning setting suggested that classical
statistical learning-theoretic measures, such as VC dimension, do not adequately explain …

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks

P Esser, L Chennuru Vankadara… - Advances in Neural …, 2021 - proceedings.neurips.cc
In recent years, several results in the supervised learning setting suggested that classical
statistical learning-theoretic measures, such as VC dimension, do not adequately explain …

Learning theory can (sometimes) explain generalisation in graph neural networks

PM Esser, LC Vankadara… - Proceedings of the 35th …, 2021 - dl.acm.org
In recent years, several results in the supervised learning setting suggested that classical
statistical learning-theoretic measures, such as VC dimension, do not adequately explain …

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks

P Esser, LC Vankadara, D Ghoshdastidar - Advances in Neural … - openreview.net
In recent years, several results in the supervised learning setting suggested that classical
statistical learning-theoretic measures, such as VC dimension, do not adequately explain …