arXiv Machine Learning September 4, 2026 By Minyi Peng, Darian Gunamardi, Ivan Tjuawinata, Yongsen Zheng, Kwok-Yan Lam

OSR: Output Space Redistribution for Adaptive Label Removal in Classification Models

Read the original on arXiv Machine Learning →

The paper introduces OSR, a method for removing labels from classification models by redistributing output space statistics to approximate retrained confidence vectors. It functions as a modular output filter, avoiding feature‑space adjustments and heavy retraining. Experiments show it matches full retraining performance while improving computational efficiency and privacy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

safety

Hugging Face Trending Papers

Oct 6

Performative Prediction with Selective Labels

Many social applications of machine learning exhibit performative effects: population behavior changes in response to deployed models. Performative prediction studies this interaction through a distri...

safety

arXiv Machine Learning

Oct 7

Performative Prediction with Selective Labels

arXiv:2610.08272v1 Announce Type: new Abstract: Many social applications of machine learning exhibit performative effects: population behavior changes in response to deployed models. Performative pre...

By Giovani Valdrighi, Isabel Valera, Marcos Medeiros Raimundo

safety

arXiv AI

Jul 14

On the Necessity of Output Distribution Reweighting for Effective Class Unlearning

arXiv:2506. 20893v5 Announce Type: replace-cross Abstract: In this paper, we reveal a significant shortcoming in class unlearning evaluations: overlooking the underlying class geometry can cause information leakage about the forgotten class.

By Ali Ebrahimpour-Boroojeny, Yian Wang, Hari Sundaram

fine-tuning benchmarks safety

arXiv Machine Learning

Jul 7

Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data

arXiv:2607. 02850v1 Announce Type: new Abstract: Meta-learning without labeled data is crucial for real-world applications, where obtaining labeled datasets can be expensive or restricted due to privacy concerns.

By Lei Sun, Yusuke Tanaka, Tomoharu Iwata

benchmarks safety

arXiv AI

Jun 4

Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning

arXiv:2605. 23595v2 Announce Type: replace-cross Abstract: The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data.

By Trinh Pham, Viet Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen

fine-tuning benchmarks

arXiv Machine Learning

Jul 31

When unlearning is free: leveraging low influence points to reduce computational costs

arXiv:2512. 05254v2 Announce Type: replace Abstract: As concerns around data privacy in machine learning grow, the ability to unlearn, or remove, specific data points from trained models becomes increasingly important.

By Anat Kleiman, Robert Fisher, Ben Deaner, Udi Wieder

safety

One email a morning, machine-written

Related stories

Performative Prediction with Selective Labels

Performative Prediction with Selective Labels

On the Necessity of Output Distribution Reweighting for Effective Class Unlearning

Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data

Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning

When unlearning is free: leveraging low influence points to reduce computational costs