noise injection
A technique used during training to improve model robustness by adding random variations to the input data to prevent overfitting.
- A Gradient Guided Diffusion Framework for Chance Constrained Programming
- CaliGCL: Calibrated Graph Contrastive Learning via Partitioned Similarity and Consistency Discrimination
- Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation
- MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning
- Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
- Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE