Research Papers 论文研究 3h ago Updated 53m ago 更新于 53分钟前 43

GLOBE: Trajectory-Aligned Gradient Matching with Structured Sparse Optimization for Coreset Selection GLOBE:轨迹对齐梯度匹配与结构化稀疏优化用于核心集选择

GLOBE introduces trajectory-aligned gradient matching for coreset selection, moving beyond single-snapshot gradients to capture evolving optimization dynamics across multiple training checkpoints A multi-order matching objective jointly aligns first-order mean and projected uncentered second-order moments of gradient trajectories to preserve full-dataset training behavior Structured sparsity via Group LASSO, Elastic Net regularization, and nonnegative budget constraints enables simultaneous grou GLOBE提出轨迹对齐的coreset选择框架,通过多检查点梯度轨迹捕捉样本在优化各阶段的影响,克服单快照梯度的局限 引入多阶匹配目标,联合对齐梯度轨迹的一阶均值和投影未中心化二阶矩,以保留完整数据集的训练行为 结合Group LASSO、Elastic Net正则化和非负预算约束,实现组级和样本级稀疏性,同时稳定强相关轨迹的权重 在六个基准和五个评估架构上验证,GLOBE在下游测试准确率上持续优于现有coreset选择方法,尤其在低保留率下表现突出

55
Hot 热度
72
Quality 质量
60
Impact 影响力

Analysis 深度分析

TL;DR

  • GLOBE introduces trajectory-aligned gradient matching for coreset selection, moving beyond single-snapshot gradients to capture evolving optimization dynamics across multiple training checkpoints
  • A multi-order matching objective jointly aligns first-order mean and projected uncentered second-order moments of gradient trajectories to preserve full-dataset training behavior
  • Structured sparsity via Group LASSO, Elastic Net regularization, and nonnegative budget constraints enables simultaneous group- and sample-level sparsity while stabilizing weights of correlated trajectories
  • Class-balanced Top-K selection ensures adequate category coverage under limited sampling budgets
  • GLOBE consistently outperforms existing coreset selection methods across six benchmarks and five architectures, especially at low retention ratios

Why It Matters

Coreset selection is critical for on-device and resource-constrained deep learning, where storing and processing full training datasets is infeasible. GLOBE addresses a key limitation of prior gradient-based methods—reliance on static, single-point gradients—by incorporating dynamic optimization trajectories, making it directly relevant to practitioners building efficient, data-efficient training pipelines for edge devices and large-scale distributed systems.

Technical Details

  • Gradient Trajectory Representation: Each training sample is represented by a gradient trajectory constructed across multiple training checkpoints, capturing its influence throughout different optimization stages rather than at a single snapshot
  • Multi-Order Matching Objective: GLOBE jointly aligns the first-order mean and projected uncentered second-order moments of gradient trajectories, preserving both directional and variance structure of the full dataset's training dynamics
  • Structured Sparsity Framework: Combines Group LASSO (group-level sparsity), Elastic Net regularization (sample-level sparsity with correlation handling), and nonnegative budget constraints to produce stable, interpretable sample weights
  • Class-Balanced Top-K Selection: After sparse weight optimization, a class-balanced Top-K procedure selects the final coreset, ensuring representative category coverage even at aggressive retention ratios
  • Empirical Validation: Evaluated across six benchmarks and five architectures, demonstrating consistent superiority over existing methods, with particularly strong gains at low retention ratios

Industry Insight

  • The shift from static to trajectory-aligned gradient matching represents a paradigm improvement for coreset selection; practitioners should consider dynamic gradient information when designing data subset strategies for on-device or federated learning
  • The combination of multi-order moment matching with structured sparsity offers a reusable template for other data selection and subset optimization problems beyond coreset selection
  • As on-device AI deployment accelerates, methods like GLOBE that enable training with significantly reduced data while preserving accuracy will become increasingly valuable for edge computing and privacy-sensitive applications

TL;DR

  • GLOBE提出轨迹对齐的coreset选择框架,通过多检查点梯度轨迹捕捉样本在优化各阶段的影响,克服单快照梯度的局限
  • 引入多阶匹配目标,联合对齐梯度轨迹的一阶均值和投影未中心化二阶矩,以保留完整数据集的训练行为
  • 结合Group LASSO、Elastic Net正则化和非负预算约束,实现组级和样本级稀疏性,同时稳定强相关轨迹的权重
  • 在六个基准和五个评估架构上验证,GLOBE在下游测试准确率上持续优于现有coreset选择方法,尤其在低保留率下表现突出

为什么值得看

该论文针对设备端训练的数据效率瓶颈提出了创新的coreset选择方案,通过轨迹对齐和多阶匹配克服了传统贪婪方法的局限。对于关注边缘计算、联邦学习和数据高效训练的从业者具有重要参考价值。

技术解析

  • GLOBE将样本选择表述为全局优化的稀疏加权问题,而非传统的贪婪或追踪选择,通过构建多个训练检查点的梯度轨迹来表征每个样本,捕捉其在优化不同阶段的影响
  • 多阶匹配目标联合对齐一阶均值和投影未中心化二阶矩,确保选择出的子集能够保留完整数据集的训练动态分布特征
  • 正则化策略融合Group LASSO和Elastic Net,在施加非负预算约束的同时诱导组级和样本级稀疏性,有效处理强相关样本的权重稳定问题
  • 类别平衡的Top-K选择机制在有限采样预算下维持充分的类别覆盖,实验覆盖六个基准和五个架构,验证了方法的有效性和泛化性

行业启示

  • 设备端AI训练对数据效率要求日益提高,GLOBE的轨迹对齐思路为边缘设备提供了可扩展的coreset选择方案,可降低计算和内存开销
  • 多阶匹配与结构化稀疏的结合为数据选择领域提供了新范式,相关技术可迁移至联邦学习、持续学习等数据受限场景
  • 低保留率下的高性能表现表明,通过优化选择策略而非单纯增加数据量,可在资源受限环境中实现接近全量训练的效果

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Research 科学研究 Training 训练 Dataset 数据集