Timeline for Using a poset or directed graph as input for a neural network
Current License: CC BY-SA 4.0
15 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 22 at 17:52 | history | edited | KhashF |
edited tags
|
|
| May 7, 2023 at 18:34 | comment | added | Joseph Van Name | It seems like poset embeddings should be used in natural language processing. In natural language processing, we typically split text into tokens such as "The oversimplification of transactions causes suffering." becoming ' The' ' oversimplification' ' of' ' transactions' ' causes' ' suffering', but we can also tokenize this text like 'The' ' over' 'simpli' 'fication' ' of' ' trans' 'actions' ' causes' ' suffer' 'ing'. Since there is typically multiple ways to split text into tokens, these tokens should be partially ordered, so we need a poset embedding to represent this. | |
| Dec 31, 2022 at 14:04 | history | reopened |
Joseph Van Name Yemon Choi Jukka Kohonen Brian Hopkins Dag Oskar Madsen |
||
| Dec 30, 2022 at 17:00 | comment | added | Joseph Van Name | If we have a graph with 1 million nodes, then the incidence matrix will have 1 trillion entries, and each row that corresponds to a node on the directed graph will have 1 million entries. Neural networks do not like dealing with very long vectors of variable length. A better option would be to associate the vertices in a digraph with vectors in $\mathbb{R}^n$ in such a way so that similar vertices are associated with similar vectors. Various graph embeddings like Node2Vec exist. But it is probably a good idea to get a handle of word embeddings before going to graph embeddings. | |
| Dec 30, 2022 at 1:04 | review | Reopen votes | |||
| Dec 31, 2022 at 14:04 | |||||
| S Oct 11, 2020 at 11:16 | history | unlocked | CommunityBot | ||
| S Oct 11, 2020 at 11:16 | history | locked | CommunityBot | ||
| S Oct 11, 2020 at 11:16 | history | closed |
user44191 Philippe Gaucher ARG Sam Hopkins Mirco A. Mannucci |
Not suitable for this site | |
| Oct 5, 2020 at 0:50 | answer | added | Mirco A. Mannucci | timeline score: 7 | |
| Oct 4, 2020 at 23:59 | comment | added | Todd Trimble | Neural networks are not my area, but couldn't you use an incidence matrix or something? | |
| Oct 4, 2020 at 23:56 | review | Close votes | |||
| Oct 11, 2020 at 11:16 | |||||
| Oct 4, 2020 at 23:20 | review | Low quality posts | |||
| Oct 5, 2020 at 0:08 | |||||
| Oct 4, 2020 at 21:49 | comment | added | Sam Hopkins | Your question might be a better fit for: stats.stackexchange.com. | |
| Oct 4, 2020 at 21:35 | review | First posts | |||
| Oct 4, 2020 at 23:11 | |||||
| Oct 4, 2020 at 21:32 | history | asked | Elias Karnoub | CC BY-SA 4.0 |