titleLightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning
authorsEilam Shapira, Alan Arazi, Shoham Grunblat, Roi Reichart
date2026-11-12
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.17600
affiliationTechnion Israel institute of technology
upvotes22 (Hugging Face Daily Papers, 2026-11-21)
linksabs pdf hf code
cite
relatedMulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes
ReLift: Dense 3D Tracking as Lifted Trajectory Repair
abstractMultimodal tabular learning involves classification and regression on tables combining structured numerical and categorical features with unstructured text and images. These unstructured fields are commonly represented by pretrained encoder embeddings reduced with principal component analysis (PCA). This reduction prioritizes input variance but may overlook information relevant to predicting the target. We introduce LightTAR, a simple, inexpensive method that adapts dimensionality reduction to the prediction task. LightTAR augments the standard PCA representation with a few target-aware features extracted jointly from the final and an intermediate encoder layer using regularized partial least squares (PLS). We evaluate LightTAR with 21 tabular models, including tree ensembles, neural networks, and tabular foundation models. LightTAR improves average predictive performance for all models and, averaged across models, improves prediction on almost every MulTaBench dataset. These gains come with a small increase in total runtime relative to PCA representations. LightTAR integrates directly into existing encoding pipelines, improving tabular learners' predictive performance without modifying the encoder or the learner.

bibtex

@misc{shapira2026lighttar,
  title={LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning},
  author={Eilam Shapira and Alan Arazi and Shoham Grunblat and Roi Reichart},
  year={2026},
  eprint={2611.17600},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.17600}
}