码字-类匹配在纠错码中作用的实证研究
The Role of Codeword-to-Class Assignments in Error-Correcting Codes: An Empirical Study
摘要：
纠错码（ECC）用于减少多类分类任务的多个二进制分类子问题。在ECC中，类别由二进制矩阵的行表示，对应于码本中的码字。码本通常是预定义的或问题相关的。给定预定义的码本，码字到类的分配传统上被忽视，码字被隐式地任意分配给类。我们的论文表明，这些分配在ECC的性能发挥了重要作用。具体来说，我们研究相似性保持分配，其中类似的码字分配给类似的类。针对现有文献中的争议，我们广泛的实验证实，相似性保持分配诱导更容易的子问题，并优于其他分配政策的泛化性能。我们发现，相似性保持分配预定义的码本成为问题相关的，而不改变其他有利的码本属性。最后，我们表明，我们的研究结果可以改善预定义的码本专用于极端分类。
英文摘要：
Error-correcting codes (ECC) are used to reduce multiclass classification tasks to multiple binary classification subproblems. In ECC, classes are represented by the rows of a binary matrix, corresponding to codewords in a codebook. Codebooks are commonly either predefined or problem dependent. Given predefined codebooks, codeword-to-class assignments are traditionally overlooked, and codewords are implicitly assigned to classes arbitrarily. Our paper shows that these assignments play a major role in the performance of ECC. Specifically, we examine similarity-preserving assignments, where similar codewords are assigned to similar classes. Addressing a controversy in existing literature, our extensive experiments confirm that similarity-preserving assignments induce easier subproblems and are superior to other assignment policies in terms of their generalization performance. We find that similarity-preserving assignments make predefined codebooks become problem-dependent, without altering other favorable codebook properties. Finally, we show that our findings can improve predefined codebooks dedicated to extreme classification.
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。
