Related papers: Transductive Model Selection under Prior Probability Shift

Transductive Model Selection under Prior Probability Shift

URL: http://arxiv.org/abs/2507.22647v1
Date: Wed, 30 Jul 2025 13:03:24 GMT
Title: Transductive Model Selection under Prior Probability Shift
Authors: Lorenzo Volpi, Alejandro Moreo, Fabrizio Sebastiani,
Abstract summary: Transductive learning is a supervised machine learning task in which the unlabelled data that require labelling are a finite set and are available at training time.<n>We propose a method, tailored to transductive classification contexts, for performing model selection when the data exhibit prior probability shift.
Score: 49.56191463229252
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are available at training time. Similarly to inductive learning contexts, transductive learning contexts may be affected by dataset shift, i.e., may be such that the IID assumption does not hold. We here propose a method, tailored to transductive classification contexts, for performing model selection (i.e., hyperparameter optimisation) when the data exhibit prior probability shift, an important type of dataset shift typical of anti-causal learning problems. In our proposed method the hyperparameters can be optimised directly on the unlabelled data to which the trained classifier must be applied; this is unlike traditional model selection methods, that are based on performing cross-validation on the labelled training data. We provide experimental results that show the benefits brought about by our method.

Related papers

Simulating Biases for Interpretable Fairness in Offline and Online Classifiers [0.35998666903987897]
Mitigation methods are critical to ensure that model outcomes are adjusted to be fair.<n>We develop a framework for synthetic dataset generation with controllable bias injection.<n>In experiments, both offline and online learning approaches are employed.
arXiv Detail & Related papers (2025-07-14T11:04:24Z)
Navigating Towards Fairness with Data Selection [27.731128352096555]
We introduce a data selection method designed to efficiently and flexibly mitigate label bias.<n>Our approach utilizes a zero-shot predictor as a proxy model that simulates training on a clean holdout set.<n>Our modality-agnostic method has proven efficient and effective in handling label bias and improving fairness across diverse datasets in experimental evaluations.
arXiv Detail & Related papers (2024-12-15T06:11:05Z)
Capturing the Temporal Dependence of Training Data Influence [100.91355498124527]
We formalize the concept of trajectory-specific leave-one-out influence, which quantifies the impact of removing a data point during training.<n>We propose data value embedding, a novel technique enabling efficient approximation of trajectory-specific LOO.<n>As data value embedding captures training data ordering, it offers valuable insights into model training dynamics.
arXiv Detail & Related papers (2024-12-12T18:28:55Z)
Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases [6.936871609178494]
We present Unlearning Information Bottleneck (UIB), a novel information-theoretic framework designed to enhance the process of machine unlearning. By proposing a variational upper bound, we recalibrate the model parameters through a dynamic prior that integrates changes in data distribution with an affordable computational cost. Our experiments across various datasets, models, and unlearning methods demonstrate that our approach effectively removes systematic patterns and biases while maintaining the performance of models post-unlearning.
arXiv Detail & Related papers (2024-05-22T21:54:05Z)
Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
We propose self-distillation as a regularization for a further pre-training stage. We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
arXiv Detail & Related papers (2022-09-30T02:25:12Z)
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)
Agree to Disagree: Diversity through Disagreement for Better Transferability [54.308327969778155]
We propose D-BAT (Diversity-By-disAgreement Training), which enforces agreement among the models on the training data. We show how D-BAT naturally emerges from the notion of generalized discrepancy.
arXiv Detail & Related papers (2022-02-09T12:03:02Z)
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
arXiv Detail & Related papers (2021-04-11T09:50:24Z)
From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems [40.427909614453526]
Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. With a meta-trained inductive bias, training of a machine learning model can be potentially carried out with reduced training data and/or time complexity. This paper provides a high-level introduction to meta-learning with applications to communication systems.
arXiv Detail & Related papers (2020-01-05T12:54:41Z)

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