CARTE: Pretraining and Transfer for Tabular Learning — mentioned by instanceofme

Thu, 09 Jan 2025 17:19:26 GMT

Related: CARTE-AI, which can also deal with multiple tables. https://soda-inria.github.io/carte/ https://arxiv.org/pdf/2402.16785 The paper includes a comparison to TabPFN v1 (among others), noting the lack of categorical & missing values handling which v2 now seems to have. Would be curious to see an updated comparison.

Paper and discussion history. A mention is not an endorsement.

CARTE: Pretraining and Transfer for Tabular Learning — mentioned by GVaroquaux

Wed, 06 Mar 2024 08:20:57 GMT

As an author, I'm happy to see this work here. For those curious about what we have been up to on the topic of tabular learning, we have found a setting where deep learning does seem to bring sizable benefits (spoiler alert, it's about being able to pre-train, and transferring to new data works best when there are some strings to be recognized): https://arxiv.org/abs/2402.16785 In the above work, pre-trained tabular models markedly outperform tree-based models (including catboost, which is a very strong baseline). As someone who has been banging on tabular data for years, I'm really excited…

Paper and discussion history. A mention is not an endorsement.

CARTE: Pretraining and Transfer for Tabular Learning · HackerPapers discussions

CARTE: Pretraining and Transfer for Tabular Learning — mentioned by instanceofme

CARTE: Pretraining and Transfer for Tabular Learning — mentioned by GVaroquaux