Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Miru, Joe, Mugon, Kwon, Minhae
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.16656
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908499395477504
author Kim, Miru
Joe, Mugon
Kwon, Minhae
author_facet Kim, Miru
Joe, Mugon
Kwon, Minhae
contents The expansion of machine learning into dynamic environments presents challenges in handling open-world problems where label shift, covariate shift, and unknown classes emerge. Post-training methods have been explored to address these challenges, adapting models to newly emerging data. However, these methods struggle when the initial pre-training is performed on class-imbalanced datasets, limiting generalization to minority classes. To address this, we propose a method that effectively handles open-world problems even when pre-training is conducted on imbalanced data. Our contrastive-based pre-training approach enhances classification performance, particularly for underrepresented classes. Our post-training mechanism generates reliable pseudo-labels, improving model robustness against open-world problems. We also introduce selective activation criteria to optimize the post-training process, reducing unnecessary computation. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art adaptation techniques in both accuracy and efficiency across diverse open-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16656
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System
Kim, Miru
Joe, Mugon
Kwon, Minhae
Machine Learning
I.2
The expansion of machine learning into dynamic environments presents challenges in handling open-world problems where label shift, covariate shift, and unknown classes emerge. Post-training methods have been explored to address these challenges, adapting models to newly emerging data. However, these methods struggle when the initial pre-training is performed on class-imbalanced datasets, limiting generalization to minority classes. To address this, we propose a method that effectively handles open-world problems even when pre-training is conducted on imbalanced data. Our contrastive-based pre-training approach enhances classification performance, particularly for underrepresented classes. Our post-training mechanism generates reliable pseudo-labels, improving model robustness against open-world problems. We also introduce selective activation criteria to optimize the post-training process, reducing unnecessary computation. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art adaptation techniques in both accuracy and efficiency across diverse open-world scenarios.
title OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System
topic Machine Learning
I.2
url https://arxiv.org/abs/2508.16656