Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sischoel
on Jan 4, 2021
|
parent
|
context
|
favorite
| on:
Why I'm Lukewarm on Graph Neural Networks
Yes, I had something mixed up here - you are completely right about CSR matrices, they should not use more memory than an adjacency list.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
