FAST：面向拓扑的频率域分布匹配用于聚类选择
FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection
AI总结：
FAST是一种无深度神经网络的分布匹配聚类选择方法，通过频域特征函数距离和渐进不匹配感知采样策略，实现高效且准确的聚类选择。
摘要：
聚类选择将大规模数据集压缩成紧凑且具有代表性的子集，从而减少训练深度神经网络的能耗和计算负担。现有方法要么是基于深度神经网络的，这些方法受特定模型参数的限制，并引入了架构偏差；要么是无深度神经网络的，这些方法依赖于启发式方法，缺乏理论保证。这两种方法都没有明确约束分布等价性，很大程度上是因为连续分布匹配被认为不适用于离散采样。此外，普遍的度量标准（例如MSE、KL、CE、MMD）无法准确捕捉高阶矩差异，导致聚类选择效果不佳。在本文中，我们提出了FAST，这是首个无深度神经网络的分布匹配聚类选择框架，将聚类选择任务作为图约束优化问题，基于谱图理论，并采用特征函数距离（CFD）来在频域中捕捉完整的分布信息。我们进一步发现，朴素的CFD在中高频区域存在“消失相梯度”问题；为了解决这个问题，我们引入了衰减相解耦CFD。此外，为了更好的收敛性，我们设计了一种渐进不匹配感知采样策略，该策略逐步从低频到高频安排频率选择，在细化局部细节之前保留全局结构，并在较少频率的情况下实现准确匹配，同时避免过拟合。广泛的实验表明，FAST在所有评估的基准上均显著优于最先进的聚类选择方法，平均准确率提高了9.12%。与其它基线聚类方法相比，它将能耗降低了96.57%，并实现了2.2倍的平均加速，凸显了其高性能和能效。
英文摘要：
Coreset selection compresses large datasets into compact, representative subsets, reducing the energy and computational burden of training deep neural networks. Existing methods are either: (i) DNN-based, which are tied to model-specific parameters and introduce architectural bias; or (ii) DNN-free, which rely on heuristics lacking theoretical guarantees. Neither approach explicitly constrains distributional equivalence, largely because continuous distribution matching is considered inapplicable to discrete sampling. Moreover, prevalent metrics (e.g., MSE, KL, CE, MMD) cannot accurately capture higher-order moment discrepancies, leading to suboptimal coresets. In this work, we propose FAST, the first DNN-free distribution-matching coreset selection framework that formulates the coreset selection task as a graph-constrained optimization problem grounded in spectral graph theory and employs the Characteristic Function Distance (CFD) to capture full distributional information in the frequency domain. We further discover that naive CFD suffers from a "vanishing phase gradient" issue in medium and high-frequency regions; to address this, we introduce an Attenuated Phase-Decoupled CFD. Furthermore, for better convergence, we design a Progressive Discrepancy-Aware Sampling strategy that progressively schedules frequency selection from low to high, preserving global structure before refining local details and enabling accurate matching with fewer frequencies while avoiding overfitting. Extensive experiments demonstrate that FAST significantly outperforms state-of-the-art coreset selection methods across all evaluated benchmarks, achieving an average accuracy gain of 9.12%. Compared to other baseline coreset methods, it reduces power consumption by 96.57% and achieves a 2.2x average speedup, underscoring its high performance and energy efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
