3 papers
cs.LG2025
Synthetic Forgetting without Access: A Few-shot Zero-glance Framework for Machine Unlearning
Qipeng Song, Nan Yang, Ziqi Xu +3
Machine unlearning aims to eliminate the influence of specific data from trained models to ensure privacy compliance. However, most existing methods assume full access to the origi…
cs.LG2025
Optimal Look-back Horizon for Time Series Forecasting in Federated Learning
Dahao Tang, Nan Yang, Yanli Li +3
Selecting an appropriate look-back horizon remains a fundamental challenge in time series forecasting (TSF), particularly in the federated learning scenarios where data is decentra…
cs.CV2025
Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
Zhiyu Zhu, Zhibo Jin, Jiayu Zhang +4
The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), whi…