TabDistill: Distilling Transformers into Neural Nets for Few-Shot Tabular Classification

• URL: http://arxiv.org/abs/2511.05704v1
• Date: Fri, 07 Nov 2025 20:46:45 GMT
• Title: TabDistill: Distilling Transformers into Neural Nets for Few-Shot Tabular Classification
• Authors: Pasan Dissanayake, Sanghamitra Dutta,
• Abstract summary: We introduce TabDistill, a new strategy to distill the pre-trained knowledge in complex transformer-based models into simpler neural networks.<n>Our framework yields the best of both worlds: being parameter-efficient while performing well with limited training data.
• Score: 11.402275466952135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based models have shown promising performance on tabular data compared to their classical counterparts such as neural networks and Gradient Boosted Decision Trees (GBDTs) in scenarios with limited training data. They utilize their pre-trained knowledge to adapt to new domains, achieving commendable performance with only a few training examples, also called the few-shot regime. However, the performance gain in the few-shot regime comes at the expense of significantly increased complexity and number of parameters. To circumvent this trade-off, we introduce TabDistill, a new strategy to distill the pre-trained knowledge in complex transformer-based models into simpler neural networks for effectively classifying tabular data. Our framework yields the best of both worlds: being parameter-efficient while performing well with limited training data. The distilled neural networks surpass classical baselines such as regular neural networks, XGBoost and logistic regression under equal training data, and in some cases, even the original transformer-based models that they were distilled from.

Related papers

• Elastic ViTs from Pretrained Models without Retraining [74.5386166956142]
  Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes.<n>We introduce SnapViT: Single-shot network approximation for pruned Vision Transformers.<n>Our approach efficiently combines gradient information with cross-network structure correlations, approximated via an evolutionary algorithm.
  arXiv  Detail & Related papers  (2025-10-20T16:15:03Z)
• Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis [63.66763657191476]
  We show that efficient numerical training and inference algorithms as low-rank computation have impressive performance for learning Transformer-based adaption. We analyze how magnitude-based models affect generalization while improving adaption. We conclude that proper magnitude-based has a slight on the testing performance.
  arXiv  Detail & Related papers  (2024-06-24T23:00:58Z)
• Learning to Continually Learn with the Bayesian Principle [36.75558255534538]
  In this work, we adopt the meta-learning paradigm to combine the strong representational power of neural networks and simple statistical models' robustness to forgetting. Since the neural networks remain fixed during continual learning, they are protected from catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-05-29T04:53:31Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• Enhancing Actuarial Non-Life Pricing Models via Transformers [0.0]
  We build on the foundation laid out by the combined actuarial neural network as well as the localGLMnet and enhance those models via the feature tokenizer transformer. The paper shows that the new methods can achieve better results than the benchmark models while preserving certain generalized linear model advantages.
  arXiv  Detail & Related papers  (2023-11-10T12:06:23Z)
• Learning to Grow Pretrained Models for Efficient Transformer Training [72.20676008625641]
  We learn to grow pretrained transformers, where we learn to linearly map the parameters of the smaller model to initialize the larger model. Experiments across both language and vision transformers demonstrate that our learned Linear Growth Operator (LiGO) can save up to 50% computational cost of training from scratch.
  arXiv  Detail & Related papers  (2023-03-02T05:21:18Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• Transfer Learning with Deep Tabular Models [66.67017691983182]
  We show that upstream data gives tabular neural networks a decisive advantage over GBDT models. We propose a realistic medical diagnosis benchmark for tabular transfer learning. We propose a pseudo-feature method for cases where the upstream and downstream feature sets differ.
  arXiv  Detail & Related papers  (2022-06-30T14:24:32Z)
• Continual Learning with Transformers for Image Classification [12.028617058465333]
  In computer vision, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. We develop a solution called Adaptive Distillation of Adapters (ADA), which is developed to perform continual learning. We empirically demonstrate on different classification tasks that this method maintains a good predictive performance without retraining the model.
  arXiv  Detail & Related papers  (2022-06-28T15:30:10Z)
• Reconstructing Training Data from Trained Neural Networks [42.60217236418818]
  We show in some cases a significant fraction of the training data can in fact be reconstructed from the parameters of a trained neural network classifier. We propose a novel reconstruction scheme that stems from recent theoretical results about the implicit bias in training neural networks with gradient-based methods.
  arXiv  Detail & Related papers  (2022-06-15T18:35:16Z)
• Churn Reduction via Distillation [54.5952282395487]
  We show an equivalence between training with distillation using the base model as the teacher and training with an explicit constraint on the predictive churn. We then show that distillation performs strongly for low churn training against a number of recent baselines.
  arXiv  Detail & Related papers  (2021-06-04T18:03:31Z)

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.