MLA方法通过模拟神经坍缩优化分类边界，提升长尾数据识别效果。
Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment
- 基于神经坍缩理论推导最优决策边界调整方式。
- 证明MLA能近似该最优调整，理论支持其有效性。
- 实验验证其在真实长尾数据上的实用性和调参指导价值。
现实世界数据分布通常高度倾斜，促使大量研究聚焦于长尾识别，以缓解训练分类模型时的不平衡问题。其中，乘法对数调整（MLA）因其简单高效而备受关注。本文从理论上解释该启发式方法的有效性，提出两步论证：首先，基于神经坍缩原理，建立通过估计特征分布来调整最优决策边界的理论；其次，证明MLA可近似该最优方法。此外，我们在多个长尾数据集上进行实验，验证了MLA在更真实场景下的实用性，并提供了调参的实验洞察。
原文摘要 · Abstract (English)
Real-world data distributions are often highly skewed. This has spurred a growing body of research on long-tailed recognition, aimed at addressing the imbalance in training classification models. Among the methods studied, multiplicative logit adjustment (MLA) stands out as a simple and effective method. What theoretical foundation explains the effectiveness of this heuristic method? We provide a justification for the effectiveness of MLA with the following two-step process. First, we develop a theory that adjusts optimal decision boundaries by estimating feature spread on the basis of neural collapse. Second, we demonstrate that MLA approximates this optimal method. Additionally, through experiments on long-tailed datasets, we illustrate the practical usefulness of MLA under more realistic conditions. We also offer experimental insights to guide the tuning of MLA hyperparameters.
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。