Verified65% confidenceFactExact time
TabPFN (Tabular Prior-Data Fitted Network) was proposed by Hollmann et al. in 2023 and pre-trains a Transformer on a large number of synthetic tabular datasets to learn the meta-task of tabular prediction.
3
Sources
65%
Confidence
Long-term
Relevance
8/5/2026
First Seen
Sources
Related Claims
Unverified2023年提出的TabPFN首次实现了表格数据的in-context learning，通过将训练样本作为上下文输入在推理时完成小规模数据集分类，无需梯度更新75% similarUnverifiedTabPFN的预训练使用由结构因果模型和贝叶斯网络等概率生成模型采样得到的合成数据集74% similarVerifiedAt inference time, TabPFN concatenates the entire training set as the Transformer input sequence and completes prediction in a single forward pass without any gradient updates.73% similarUnverifiedTabPFN属于基于模型的元学习类别，将整个学习算法编码到Transformer的权重中，因此推理时不需要显式的参数更新过程69% similarUnverifiedAt inference time, TabPFN feeds a small number of examples together with the input to be predicted directly into a forward pass, requiring no backpropagation, GPU training clusters, or persistently saved new model files.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/689007API
curl https://kongchang.com/api/v1/knowledge/claims/689007MCP
get_claim(id=689007)