Hugging Face Trending Papers

Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning

Read the original on Hugging Face Trending Papers →

Parameter-efficient fine-tuning still leaves a broad space of behavior-changing updates reachable, so a poisoned objective can be represented and optimized. We study an alternative: adaptation constrained to the subspace estimated from a trusted pool of existing task adapters.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Jul 17

Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning

arXiv:2607. 14367v1 Announce Type: new Abstract: Federated fine-tuning of large pre-trained models increasingly relies on Low-Rank Adaptation (LoRA) to reduce communication and computation, but heterogeneous clients can make adapter aggregation unstable.

By Haobo Zhang, Jiankun Wang, Suraj Rajendran, Weishen Pan, Lam Tsoi, Yong Chen, Fei Wang, Jiayu Zhou