TabICL scales in-context learning to large tabular data via column-then-row attention for row embeddings followed by a transformer, matching TabPFNv2 speed and performance while outperforming it and CatBoost on datasets over 10K samples.
Multi-Source Domain Adaptation with Mixture of Experts
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example and different source domains. This relationship, expressed by a point-to-set metric, determines how to combine predictors trained on various domains. The metric is learned in an unsupervised fashion using meta-training. Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer.
fields
cs.LG 2representative citing papers
CS-ARM-BN uses negative control samples to stabilize Batch Normalization statistics in a meta-learning framework, achieving robust MoA classification on new experimental batches under label shift and small sample sizes.
citing papers explorer
-
TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
TabICL scales in-context learning to large tabular data via column-then-row attention for row embeddings followed by a transformer, matching TabPFNv2 speed and performance while outperforming it and CatBoost on datasets over 10K samples.
-
Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls
CS-ARM-BN uses negative control samples to stabilize Batch Normalization statistics in a meta-learning framework, achieving robust MoA classification on new experimental batches under label shift and small sample sizes.