all AI news
On dimensionality of feature vectors in MPNNs
Feb. 7, 2024, 5:42 a.m. | C\'esar Bravo Alexander Kozachinskiy Crist\'obal Rojas
cs.LG updates on arXiv.org arxiv.org
Morris et al.~show their simulation result with ReLU activation function and $O(n)$-dimensional feature vectors, where $n$ is the number of nodes of the graph. Recently, by introducing randomness into the architecture, Aamand et al.~(NeurIPS'22) were able to improve this bound to $O(\log n)$-dimensional feature vectors, although at the expense of guaranteeing perfect simulation …
aaai cs.lg dimensionality feature function graph graphs networks neural networks power relu show simulation test vectors
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Software Engineer, Generative AI (C++)
@ SoundHound Inc. | Toronto, Canada