Dataset Distillation Using Parameter Pruning
This work addresses dataset distillation for machine learning practitioners, but it appears incremental as it builds on existing methods with a specific enhancement.
The authors tackled dataset distillation by introducing a method based on parameter pruning to synthesize more robust distilled datasets and improve performance, with experimental results on two benchmark datasets demonstrating its superiority.
In this study, we propose a novel dataset distillation method based on parameter pruning. The proposed method can synthesize more robust distilled datasets and improve distillation performance by pruning difficult-to-match parameters during the distillation process. Experimental results on two benchmark datasets show the superiority of the proposed method.