Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

ICLR 2026 Conference Submission12459 Authors

Keywords: Semi-Supervised Noise Adaptation, Noise Adaptation, Semi-supervised Learning, Distribution Alignment

TL;DR: Transferring knowledge from a structured noise domain to facilitate the learning in the target domain

Abstract:

Transfer learning aims to facilitate the learning of a target domain by transferring knowledge from a source domain.
The source domain typically contains
semantically meaningful samples (*e.g.*, images) to facilitate effective knowledge transfer. However, a recent study observes that the noise domain constructed from simple distributions (*e.g.*, Gaussian distributions) can serve as a surrogate source domain in the semi-supervised setting, where only a small proportion of target samples are labeled while most remain unlabeled.
Based on this surprising observation, we formulate a novel problem termed *Semi-Supervised Noise Adaptation* (SSNA), which aims to leverage a synthetic noise domain to improve the generalization of the target domain. To address this problem, we first establish a generalization bound characterizing the effect of the noise domain on generalization, based on which we propose a Noise Adaptation Framework (NAF). Extensive experiments demonstrate that NAF effectively utilizes the noise domain to tighten the generalization bound of the target domain, thereby achieving improved performance.
The codes are available at https://anonymous.4open.science/r/SSNA.

Primary Area: transfer learning, meta learning, and lifelong learning

Submission Number: 12459