Train on Validation (ToV): Fast data selection with applications to fine-tuning
- URL: http://arxiv.org/abs/2510.00386v1
- Date: Wed, 01 Oct 2025 00:55:39 GMT
- Title: Train on Validation (ToV): Fast data selection with applications to fine-tuning
- Authors: Ayush Jain, Andrea Montanari, Eren Sasoglu,
- Abstract summary: State-of-the-art machine learning often follows a two-stage process: $(i)$pre-training on large, general-purpose datasets; $(ii)$fine-tuning on task-specific data.<n>Existing data selection methods treat target samples as a validation set and estimate the effect of adding or removing a single sample from the training pool.<n>We propose a simpler and faster alternative that inverts the usual role of train and validation.<n>Our key insight is that the training samples most affected by fine-tuning on a small validation set tend to be the most beneficial for
- Score: 12.967061784324427
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: State-of-the-art machine learning often follows a two-stage process: $(i)$~pre-training on large, general-purpose datasets; $(ii)$~fine-tuning on task-specific data. In fine-tuning, selecting training examples that closely reflect the target distribution is crucial. However, it is often the case that only a few samples are available from the target distribution. Existing data selection methods treat these target samples as a validation set and estimate the effect of adding or removing a single sample from the training pool by performing inference on the validation set. We propose a simpler and faster alternative that inverts the usual role of train and validation: we perform inference on the training pool before and after fine-tuning on the validation set. We then select samples whose predictions change the most. Our key insight is that the training samples most affected by fine-tuning on a small validation set tend to be the most beneficial for reducing test loss on the target distribution. Experiments on instruction tuning and named entity recognition tasks show that, in most cases, our method achieves lower test log-loss than state-of-the-art approaches. We support our findings with theoretical analysis.
Related papers
- Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples [62.13094877228772]
We show that mislabeled examples correctly predicted by the model early in the training process are particularly harmful to model performance.<n>We propose Early Cutting, which employs the model's later training state to re-select the confident subset identified early in training.
arXiv Detail & Related papers (2025-02-12T09:12:45Z) - Test-Time Alignment via Hypothesis Reweighting [56.71167047381817]
Large pretrained models often struggle with underspecified tasks.<n>We propose a novel framework to address the challenge of aligning models to test-time user intent.
arXiv Detail & Related papers (2024-12-11T23:02:26Z) - BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping [64.8477128397529]
We propose a training-required and training-free test-time adaptation framework.
We maintain a light-weight key-value memory for feature retrieval from instance-agnostic historical samples and instance-aware boosting samples.
We theoretically justify the rationality behind our method and empirically verify its effectiveness on both the out-of-distribution and the cross-domain datasets.
arXiv Detail & Related papers (2024-10-20T15:58:43Z) - Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels [22.24077757409148]
We propose a noIse-Tolerant Expert Model (ITEM) for debiased learning in sample selection.<n>Specifically, to mitigate the training bias, we design a robust network architecture that integrates with multiple experts.<n>By training on the mixture of two class-discriminative mini-batches, the model mitigates the effect of the imbalanced training set.
arXiv Detail & Related papers (2024-01-24T10:37:28Z) - How Low Can You Go? Surfacing Prototypical In-Distribution Samples for Unsupervised Anomaly Detection [48.30283806131551]
We show that UAD with extremely few training samples can already match -- and in some cases even surpass -- the performance of training with the whole training dataset.
We propose an unsupervised method to reliably identify prototypical samples to further boost UAD performance.
arXiv Detail & Related papers (2023-12-06T15:30:47Z) - One-bit Supervision for Image Classification: Problem, Solution, and
Beyond [114.95815360508395]
This paper presents one-bit supervision, a novel setting of learning with fewer labels, for image classification.
We propose a multi-stage training paradigm and incorporate negative label suppression into an off-the-shelf semi-supervised learning algorithm.
In multiple benchmarks, the learning efficiency of the proposed approach surpasses that using full-bit, semi-supervised supervision.
arXiv Detail & Related papers (2023-11-26T07:39:00Z) - Test-Time Distribution Normalization for Contrastively Learned
Vision-language Models [39.66329310098645]
One of the most representative approaches proposed recently known as CLIP has garnered widespread adoption due to its effectiveness.
This paper reveals that the common downstream practice of taking a dot product is only a zeroth-order approximation of the optimization goal, resulting in a loss of information during test-time.
We propose Distribution Normalization (DN), where we approximate the mean representation of a batch of test samples and use such a mean to represent what would be analogous to negative samples in the InfoNCE loss.
arXiv Detail & Related papers (2023-02-22T01:14:30Z) - POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution
Samples [19.311470287767385]
We propose to use out-of-distribution samples, i.e., unlabeled samples coming from outside the target classes, to improve few-shot learning.
Our approach is simple to implement, agnostic to feature extractors, lightweight without any additional cost for pre-training, and applicable to both inductive and transductive settings.
arXiv Detail & Related papers (2022-06-08T18:59:21Z) - CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time.
We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
arXiv Detail & Related papers (2022-06-01T03:02:07Z) - Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions.
In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data.
We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
arXiv Detail & Related papers (2022-01-11T23:01:12Z)
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.