The paper presents a scalable method for meta‑learning interpretable decision trees by generating synthetic pre‑training data. It samples near‑optimal trees to create large, realistic datasets and uses the MetaTree transformer architecture to match the performance of real‑world pre‑training or costly optimal tree training. This approach cuts computational costs, offers flexible data generation, and supports efficient, scalable meta‑learning of decision trees.
By Kyaw Hpone Myint, Zhe Wu, Alexandre G. R. Day, Giri Iyengar
arXiv:2511. 15941v2 Announce Type: replace-cross Abstract: Tabular data underpins decisions across science, industry, and public services.
By David Bonet, Mar\c{c}al Comajoan Cara, Alvaro Calafell, Daniel Mas Montserrat, Alexander G. Ioannidis
arXiv:2609.28122v1 Announce Type: cross
Abstract: Neural Processes (NPs) are model-based meta-learners that implicitly learn a stochastic process and adapt to a new task from a small context set. Mos...
By Andrea Nava, Ken R\"olli, Armin Begic, Fabio Sigrist
Neural Processes (NPs) are model-based meta-learners that implicitly learn a stochastic process and adapt to a new task from a small context set. Most extensions of NPs focus on improving the neural n...
OrionMoE-v1.0 is a compact tabular foundation model that uses a dual‑axis Transformer and a sparse mixture‑of‑experts architecture to perform in‑context learning on labeled support tables. It selectively activates experts along the feature axis, guided by both individual feature representations and overall dataset context, enabling adaptive computation across diverse tabular problems. Pretrained on synthetic classification tasks, it achieves competitive performance on multiple benchmarks, especially on small‑context, high‑dimensional, and class‑imbalanced datasets.
By Mohamed Bouadi, Nassim Bouarour, Aditya Tanna, Vinay Kumar Sankarapu
TabMF is a framework that repurposes pretrained tabular foundation models (TFMs) as encoders for supervised datasets, adding a dataset-level readout and fine‑tuning via contrastive post‑training on synthetic views. The authors instantiate TabMF on TabICLv2 and TabPFN‑2.5 and evaluate the resulting representations on six tasks involving unseen real datasets. The approach achieves the best aggregate performance among both learned and classical dataset representations, excelling in dataset retrieval, compact benchmark construction, and distribution‑shift severity assessment.
By Rafiq Kamel, Nicolas Atienza, Aziz Fouch\'e, Nicola Cancedda, Josif Grabocka