Methods › General › Deep Tabular Learning › SCARF
SCARF
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SCARF is a simple, widely-applicable technique for contrastive learning, where views are formed by corrupting a random subset of features. When applied to pre-train deep neural networks on the 69 real-world, tabular classification datasets from the OpenML-CC18 benchmark, SCARF not only improves classification accuracy in the fully-supervised setting but does so also in the presence of label noise and in the semi-supervised setting where only a fraction of the available training data is labeled.
Papers archive 2025-07-28
7 shown of 7, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
A System for Comprehensive Assessment of RAG Frameworks 10 Apr 2025 · 1 repository · arXiv:2504.07803
-
Some Characterizations of TTC in Multiple-Object Reallocation Problems 7 Apr 2024 · 0 repositories · arXiv:2404.04822
-
House-Swapping with Objective Indifferences 15 Jun 2023 · 0 repositories · arXiv:2306.09529
-
Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data 24 Mar 2023 · 2 repositories · arXiv:2303.14080
-
Revealed Preferences of One-Sided Matching 25 Oct 2022 · 0 repositories · arXiv:2210.14388
-
Capturing and Animation of Body and Clothing from Monocular Video 4 Oct 2022 · 1 repository · arXiv:2210.01868
-
SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption 29 Jun 2021 · 1 repository · arXiv:2106.15147Syntology ran 1 of 3 samples · 2 unverified
Tasks archive 2025-07-28
8 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Contrastive Learning | 2 |
| Combinatorial Optimization | 1 |
| RAG | 1 |
| Representation Learning | 1 |
| Retrieval | 1 |
| Retrieval-augmented Generation | 1 |
| Virtual Try-on | 1 |
| tabular-classification | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections