让模型自己选关键数据，用30%数据达到98.9%性能。
ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction
- 用可微分对抗机制自动挑选对任务重要的样本
- 仅用30%数据就保持98.9%性能，远超传统方法
- 适合追求高效训练的深度学习研究者
大规模数据集常含冗余信息，增加计算开销却不提升泛化能力。现有数据缩减方法多为任务无关，易丢弃重要边界样本，导致性能不佳。我们提出可微分对抗框架ASSS，将数据缩减建模为可学习选择器与任务网络之间的极小极大博弈。通过Gumbel-Softmax松弛，ASSS实现端到端梯度传播，并在信息瓶颈原理上有理论支撑。多个基准测试显示，ASSS仅使用30%数据即可达到98.9%性能保留率（PRR），显著优于随机采样、K-means及基于梯度的方法。可视化表明，ASSS优先保留决策边界附近的样本。该框架可扩展、全可微，易于集成至现有训练流程。本工作提出了任务感知数据缩减的新范式，直接优化子集选择以服务下游目标，为现代深度学习的可扩展性问题提供了一种原则性且实用的解决方案。
原文摘要 · Abstract (English)
Massive datasets often contain redundancy that inflates computational costs without improving generalization. Existing data reduction methods are typically task-agnostic, discarding informative boundary samples and yielding suboptimal performance. We propose Adversarial Soft-Selection Subsampling (ASSS), a differentiable framework that casts data reduction as a minimax game between a learnable selector and a task network. Using Gumbel-Softmax relaxation, ASSS enables end-to-end gradient flow and is theoretically grounded in the information bottleneck principle. Experiments on multiple benchmarks show that ASSS achieves a performance retention rate (PRR) of 98.9% while using only 30% of the data, significantly outperforming random sampling, K-means, and gradient-based methods. Visualizations confirm that ASSS preferentially retains samples near decision boundaries. The framework is scalable, fully differentiable, and easily integrated into existing training pipelines. This work introduces a new paradigm for task-aware data reduction that directly optimizes subset selection for the downstream objective, offering a principled and practical solution to the scalability challenges in modern deep learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。