TGTGInsighttelegram intelligenceLIVE / telegram public index
← Graph Machine Learning
Graph Machine Learning avatar

TGINSIGHT POST

Post #340

@graphml

Graph Machine Learning

Vues1,900Nombre de vues
Publié12 nov.12/11/2020 08:34
Contenu

Contenu du post

Papers and Scores at ICLR 2021 You can see a ranked list of all papers at ICLR 2021 here (~3000 papers) and only for graph papers here (200+ papers). These scores are before rebuttal, so they can change in the final ranking. With 20% acceptance rate (which is a bit low for ICLR), the average score should be about 6, in order to get accepted. The median score now is 5.25. There are many graph papers are at the top of the list, including the top-1 paper. And from the last year here are some insights: (1) Every third paper on graphs is accepted, clear indication GML is becoming popular; (2) On average it's needed [6,6,8] to get accepted, [6,6,6] would be borderline. (3) AC can sometimes save a paper, even if got low scores. This is rather good, meaning that reviewers are not the only ones who decide. (4) Likewise, AC can reject a paper, even if it is unanimous accept by the reviewers. I think that happens mostly because the paper does not present enough experimental comparison to SOTA.