The paper introduces CATTLE, a transfer learning framework for disjoint tabular datasets that eliminates the need for shared features by leveraging generalized context learned through transformer projection weights. By using key, value, and query weights from source and target domains, CATTLE performs cross‑domain attention transfer in a data‑agnostic manner. Experiments on ten source‑target pairs demonstrate that CATTLE outperforms nine state‑of‑the‑art baselines, achieving the best average rank (2.9) and a 3.7% AUROC improvement.
arXiv:2603. 07523v3 Announce Type: replace Abstract: Transferring knowledge by fine-tuning large-scale pre-trained networks has become a standard paradigm for downstream tasks, yet the knowledge of a pre-trained model is tightly coupled with monolithic architecture, which restricts flexible reuse across models of varying scales.
arXiv:2607. 17467v1 Announce Type: cross Abstract: Few-shot Test-Time Domain Adaptation (FSTT-DA) seeks to adapt models to novel domains using only a handful of unlabeled target samples.
arXiv:2607. 00479v1 Announce Type: new Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning.
SOMTab is a Set-Order Mamba architecture designed for efficient tabular in-context learning. It separates representation construction from query-conditioned retrieval, using Mamba-based state‑space mixing to build compact row and column representations while retaining attention for final prediction. The model, along with a synthetic prior called DCH‑TailMix, achieves performance comparable to Transformer‑based tabular foundation models but with faster inference and lower GPU memory usage.
arXiv:2608. 09091v1 Announce Type: cross Abstract: Transfer learning is particularly useful in settings with limited training data, and within image classification it is common to transfer learn upon massive datasets like ImageNet , CIFAR-100, or COCO .
The paper investigates whether deep transformer layers require context from the residual stream to compute value vectors. It finds that allowing deeper layers to use a context‑free value vector—preserving original token information—significantly improves performance, and adding context afterward yields little extra benefit. The authors introduce Bank of Values (BoV), a lookup table of token‑specific value vectors for the last third of layers, which reduces compute and memory while matching or surpassing prior methods on large models.
The paper demonstrates that a tabular foundation model can achieve strong generalization using only a single real table for self‑supervised pre‑training, challenging the belief that large synthetic or real datasets are necessary. By systematically pre‑training and evaluating across diverse benchmarks, the authors show that the number and quality of tasks that can be derived from a dataset are critical for downstream performance. This finding suggests that carefully constructed task sets from limited data can enable effective transfer learning in tabular models.
arXiv:2602. 14761v2 Announce Type: replace-cross Abstract: Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability.
arXiv:2607. 13425v1 Announce Type: cross Abstract: Learning effectively from limited data is critical in domains like security where labeled examples are scarce.
The paper investigates how Tabular Foundation Models (TFMs) can achieve strong transfer learning by self‑supervised pre‑training on a single real table. It finds that a table’s usefulness is largely determined by its number of features rather than instances, and that fine‑grained column‑level preprocessing improves downstream performance while dataset‑level filtering does not. The authors propose that tabular in‑context generalization is primarily retrieval‑based, with models learning to identify and aggregate relevant examples from the provided context.
The paper critically evaluates common few‑shot learning protocols that rely on pre‑training a model on a large auxiliary set with classes disjoint from the target but drawn from the same visual domain. By comparing no pre‑training, class‑disjoint in‑domain pre‑training, supervised out‑of‑domain pre‑training, and label‑free out‑of‑domain pre‑training across eight datasets and three architectures, the authors find that in‑domain pre‑training yields a 33.41‑point average improvement, while out‑of‑domain pre‑training offers a 23.75‑point gain, revealing a 9.66‑point optimistic bias due to domain overlap. They also demonstrate that a label‑free augmentation strategy can match supervised out‑of‑domain performance and propose a descriptor‑based source‑selection method that closely approximates oracle selection, underscoring the need to move beyond in‑domain pre‑training as the default evaluation protocol.
The paper introduces an importance‑scoring metric for multi‑head transformer attention heads applied to tabular data, a domain where transformers have been less studied. Experiments on 40 diverse tabular datasets show that removing heads with the lowest importance scores has minimal impact on performance, while removing the most important head first causes the largest drop. The study finds that important heads are distributed across layers and vary significantly across different tabular schemas, suggesting that the proposed score can help reduce redundancy and improve transformer efficiency.