TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data

• URL: http://arxiv.org/abs/2605.20234v1
• Date: Sat, 16 May 2026 15:02:03 GMT
• Title: TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
• Abstract summary: TabPFN-MT is trained on an expanded multi-target synthetic prior to capture inter-task dependencies in context.<n>It is uniquely specialized for small-to-medium datasets by relying on in-context learning.<n>It achieves an overall Accuracy rank of 4.89, the highest average rank among all models tested.
• Score: 8.150109591980108
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Prior-Data Fitted networks (PFNs) have been very successful in tabular contexts, handling prediction tasks in context. However, they are designed for single-task inference, meaning that predicting several target values within a context requires repeated forward calls and precludes inter-task information sharing. We propose TabPFN-MT, which is trained on an expanded multi-target synthetic prior to capture inter-task dependencies in context. This model uses an expanded $y$-encoder and a shared decoder head to enable multitask in-context learning and simultaneous inference. The model is uniquely specialized for small-to-medium datasets by relying on in-context learning rather than traditional gradient-based training. Within this regime (averaging fewer than 1,000 samples), extensive evaluations across 344 datasets demonstrate that TabPFN-MT establishes a new state-of-the-art for deep tabular multitask learning. Furthermore, despite the inherent compute asymmetry of joint optimization, our model remains highly competitive with the latest state-of-the-art single-task ensembles. Notably, on multitask datasets it achieves an overall Accuracy rank of 4.89, the highest average rank among all models tested. Crucially, TabPFN-MT delivers this highly competitive performance while reducing the inference cost for $T$ tasks from $O(T)$ to $O(1)$ forward passes, offering a massive computational efficiency improvement for multi-target tabular applications.

Related papers

• TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training [29.962039479618543]
  We introduce TADS (Task-Aware Data Selection), a novel framework for multi-task multimodal pre-training.<n> TADS integrates Intrinsic Quality, Task Relevance, and Distributional Diversity into a learnable value function.<n>A feedback-driven meta-learning mechanism adaptively refines the selection strategy based on proxy model performance.
  arXiv  Detail & Related papers  (2026-02-05T03:08:45Z)
• StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets [14.867396697566257]
  We extend the partial learning setup to a zero-shot setting, training a multi-task model on multiple datasets, each labeled for only a subset of tasks.<n>Our method, StableMTL, repurposes image generators for latent regression.<n>Instead of per-task losses requiring careful balancing, a unified latent loss is adopted, enabling seamless scaling to more tasks.
  arXiv  Detail & Related papers  (2025-06-09T17:59:59Z)
• Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks [69.38572074372392]
  We present the first results proving that feature learning occurs during training with a nonlinear model on multiple tasks. Our key insight is that multi-task pretraining induces a pseudo-contrastive loss that favors representations that align points that typically have the same label across tasks.
  arXiv  Detail & Related papers  (2023-07-13T16:39:08Z)
• Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning [101.66860222415512]
  Multi-Task Diffusion Model (textscMTDiff) is a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis. For generative planning, we find textscMTDiff outperforms state-of-the-art algorithms across 50 tasks on Meta-World and 8 maps on Maze2D.
  arXiv  Detail & Related papers  (2023-05-29T05:20:38Z)
• $\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation [30.551283402200657]
  $pi$-Tuning is a universal parameter-efficient transfer learning method for vision, language, and vision-language tasks. It aggregates the parameters of lightweight task-specific experts learned from similar tasks to aid the target downstream task.
  arXiv  Detail & Related papers  (2023-04-27T17:49:54Z)
• Multi-Task Meta Learning: learn how to adapt to unseen tasks [4.287114092271669]
  This work proposes Multi-task Meta Learning (MTML), integrating two learning paradigms Multi-Task Learning (MTL) and meta learning. The fundamental idea is to train a multi-task model, such that when an unseen task is introduced, it can learn in fewer steps whilst offering a performance at least as good as conventional single task learning. MTML achieves state-of-the-art results for three out of four tasks for the NYU-v2 dataset and two out of four for the taskonomy dataset.
  arXiv  Detail & Related papers  (2022-10-13T12:59:54Z)
• Multi-task Active Learning for Pre-trained Transformer-based Models [22.228551277598804]
  Multi-task learning, in which several tasks are jointly learned by a single model, allows NLP models to share information from multiple annotations. This technique requires annotating the same text with multiple annotation schemes which may be costly and laborious. Active learning (AL) has been demonstrated to optimize annotation processes by iteratively selecting unlabeled examples.
  arXiv  Detail & Related papers  (2022-08-10T14:54:13Z)
• Task Adaptive Parameter Sharing for Multi-Task Learning [114.80350786535952]
  Adaptive Task Adapting Sharing (TAPS) is a method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
  arXiv  Detail & Related papers  (2022-03-30T23:16:07Z)
• Exploring Relational Context for Multi-Task Dense Prediction [76.86090370115]
  We consider a multi-task environment for dense prediction tasks, represented by a common backbone and independent task-specific heads. We explore various attention-based contexts, such as global and local, in the multi-task setting. We propose an Adaptive Task-Relational Context module, which samples the pool of all available contexts for each task pair.
  arXiv  Detail & Related papers  (2021-04-28T16:45:56Z)
• Low Resource Multi-Task Sequence Tagging -- Revisiting Dynamic Conditional Random Fields [67.51177964010967]
  We compare different models for low resource multi-task sequence tagging that leverage dependencies between label sequences for different tasks. We find that explicit modeling of inter-dependencies between task predictions outperforms single-task as well as standard multi-task models.
  arXiv  Detail & Related papers  (2020-05-01T07:11:34Z)
• MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning [82.62433731378455]
  We show that tasks with high affinity at a certain scale are not guaranteed to retain this behaviour at other scales. We propose a novel architecture, namely MTI-Net, that builds upon this finding.
  arXiv  Detail & Related papers  (2020-01-19T21:02:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.