Hugging Face Daily Papers · · 3 min read

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Transferring knowledge from a structured noise domain to facilitate the learning in the target domain</p>\n","updatedAt":"2026-06-04T12:02:30.079Z","author":{"_id":"668bb3b14c25c09b01815a55","avatarUrl":"/avatars/5d46301dd5d7641e3da05b0ad560efee.svg","fullname":"Yuan Yao","name":"yyyaoyuan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8727948069572449},"editors":["yyyaoyuan"],"editorAvatarUrls":["/avatars/5d46301dd5d7641e3da05b0ad560efee.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.00558","authors":[{"_id":"6a2168af3490a593e87b0ebc","name":"Yuan Yao","hidden":false},{"_id":"6a2168af3490a593e87b0ebd","name":"Jin Song","hidden":false},{"_id":"6a2168af3490a593e87b0ebe","name":"Huixia Li","hidden":false},{"_id":"6a2168af3490a593e87b0ebf","name":"Tongtong Yuan","hidden":false},{"_id":"6a2168af3490a593e87b0ec0","name":"Jiaqi Wu","hidden":false},{"_id":"6a2168af3490a593e87b0ec1","name":"Yu Zhang","hidden":false}],"publishedAt":"2026-05-30T00:00:00.000Z","submittedOnDailyAt":"2026-06-04T00:00:00.000Z","title":"Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain","submittedOnDailyBy":{"_id":"668bb3b14c25c09b01815a55","avatarUrl":"/avatars/5d46301dd5d7641e3da05b0ad560efee.svg","isPro":false,"fullname":"Yuan Yao","user":"yyyaoyuan","type":"user","name":"yyyaoyuan"},"summary":"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 leverages the noise domain to tighten the generalization bound of the target domain, leading to improved performance. The codes are available at https://github.com/AIResearch-Group/SSNA.","upvotes":1,"discussionId":"6a2168b03490a593e87b0ec2","githubRepo":"https://github.com/AIResearch-Group/SSNA","githubRepoAddedBy":"user","ai_summary":"A novel semi-supervised learning approach uses synthetic noise domains as source domains to improve target domain generalization through a proposed noise adaptation framework.","ai_keywords":["transfer learning","source domain","target domain","semi-supervised learning","noise domain","generalization bound","noise adaptation framework","synthetic data"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":0},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"668bb3b14c25c09b01815a55","avatarUrl":"/avatars/5d46301dd5d7641e3da05b0ad560efee.svg","isPro":false,"fullname":"Yuan Yao","user":"yyyaoyuan","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.00558.md"}">
Papers
arxiv:2606.00558

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

Published on May 30
· Submitted by
Yuan Yao
on Jun 4
Authors:
,
,
,
,
,

Abstract

A novel semi-supervised learning approach uses synthetic noise domains as source domains to improve target domain generalization through a proposed noise adaptation framework.

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 leverages the noise domain to tighten the generalization bound of the target domain, leading to improved performance. The codes are available at https://github.com/AIResearch-Group/SSNA.

Community

Paper submitter about 14 hours ago

Transferring knowledge from a structured noise domain to facilitate the learning in the target domain

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.00558
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.00558 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.00558 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.00558 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers