Learning representations of learning representations

arXiv:2404.08403v1 Announce Type: cross
Abstract: The ICLR conference is unique among the top machine learning conferences in that all submitted papers are openly available. Here we present the ICLR dataset consisting of abstracts of all 24 thousand ICLR submissions from 2017-2024 with meta-data, decision scores, and custom keyword-based labels. We find that on this dataset, bag-of-words representation outperforms most dedicated sentence transformer models in terms of $k$NN classification accuracy, and the top performing language models barely outperform TF-IDF. We see …

abstract arxiv conference conferences cs.cl cs.dl cs.lg data dataset decision iclr labels machine machine learning meta openly papers type