this post was submitted on 14 Jun 2024
2 points (60.0% liked)

Machine Learning

478 readers
2 users here now

A community for posting things related to machine learning

Icon base by Lorc under CC BY 3.0 with modifications to add a gradient

founded 1 year ago
MODERATORS
Ategon@programming.dev
Akisamb@programming.dev
ericjmorey@programming.dev
2
LGGMs a new class of graph generative models trained on a large corpus of graphs (www.marktechpost.com)
submitted 5 months ago by Akisamb@programming.dev to c/machine_learning@programming.dev
2 comments fedilink hide all child comments
top 2 comments
sorted by: hot top controversial new old
[โ€“] ericjmorey@programming.dev 4 points 5 months ago* (last edited 5 months ago) (1 children)

The down votes from non-subscribed accounts are amusing to me. These people clearly are looking for their "all" feed to be curated in some way. Ironically, machine learning could potentially help with that, but there are many people burnt out by the hype cycle (I don't blame them).

Regarding the article. It looks like the advancement here is finding methods to efficiently use sets of graphs which are an order of magnitude larger than prior methods could use for training? They also seem to have used more sets of graphs than prior models across a wider set of domains. Am I reading this correctly?

[โ€“] Akisamb@programming.dev 2 points 5 months ago

Huh, your comment made look if there were personalized recommendation algorithms running on lemmy. From what I found, it appears that Lemmy does not use personalized recommendation algorithms : https://join-lemmy.org/docs/contributors/07-ranking-algo.html

The specific function used for ranking is here : https://github.com/LemmyNet/lemmy/blob/4ba6221e04ab3e186669aeaa890d23b1e3f3d1a9/crates/db_schema/replaceable_schema/utils.sql#L18

I'm wondering how hard it would be to adapt the code to customize the score for every user, instead of it being global.

I makes it look like the advancement here is finding methods to efficiently use sets of graphs which are an order of magnitude larger than prior methods could use for training? They also seem to have used more sets of graphs than prior models across a wider set of domains. Am I reading this correctly?

I find it challenging to gauge the paper's impact fully, as this isn't my area of expertise. However, the ability to use diverse graphs in a single model surprised me and seemed worth sharing.