TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
hub
TabNet: Attentive Interpretable Tabular Learning
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
fields
cs.LG 10representative citing papers
Individually calibrated predictors become collectively miscalibrated under Brier-optimal strategic responses with positive belief correlations, but VCG aggregation restores dominant-strategy incentive compatibility and near-optimal performance.
BISN achieves 0.93 mean leave-one-batch-out accuracy on 2700 NIR spectra from three insect species across three batches, outperforming baselines by 4% while decisions align with lipid and protein absorption regions.
FlagGAM builds sparse univariate rule bases from features and feeds them into a restricted additive model, achieving competitive accuracy with superior robustness to missingness and noise on tabular benchmarks.
Adds a trainable feature selection layer to NAM and NBM to cut computational cost, enable two-input interaction networks in high dimensions, and match or exceed state-of-the-art GAM performance.
GOTabPFN combines GO-LR ordering (equivalent to weighted minimum linear arrangement) and NSC compression to enable practical TabPFN-style prediction on HDLSS tabular data under tight token budgets, improving stability and accuracy.
Tabular foundation models outperform standard methods in credit risk PD and LGD tasks, with larger gains on smaller datasets when used out-of-the-box.
Physics-informed GNNs with four detector-aware graph constructions and a custom message passing layer achieve MAE 0.8525 for pT estimation on CMS trigger data with over 55% fewer parameters than baselines.
FCNN maps tabular features to fuzzy memberships, arranges them as images, and uses CNNs to classify, reporting competitive or superior results versus DT, SVM, FNN, Bayes, and RF on six generated noisy datasets.
citing papers explorer
-
When Individually Calibrated Models Become Collectively Miscalibrated
Individually calibrated predictors become collectively miscalibrated under Brier-optimal strategic responses with positive belief correlations, but VCG aggregation restores dominant-strategy incentive compatibility and near-optimal performance.