分类器是魔鬼：用解耦分析研究长尾关系分类
The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis
摘要：
长尾关系分类是一个具有挑战性的问题，因为头部类可能会主导训练阶段，从而导致尾部性能的恶化。现有的解决方案通常通过类平衡策略来解决这个问题，例如，数据重采样和损失重加权，但所有这些方法都坚持表示和分类器的纠缠学习模式。在这项研究中，我们对长尾问题进行了深入的实证调查，发现具有实例平衡采样的预训练模型已经捕获了所有类的良好学习表示;此外，仅通过调整分类器就可以以低成本实现更好的长尾分类能力。受此启发，我们提出了一个强大的分类器与细心的关系路由，分配软权重自动聚合的关系。在两个数据集上的实验证明了该方法的有效性。代码和数据集可在https://github.com/zjunlp/deepke上获得。
英文摘要：
Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance. Existing solutions usually address this issue via class-balancing strategies, e.g., data re-sampling and loss re-weighting, but all these methods adhere to the schema of entangling learning of the representation and classifier. In this study, we conduct an in-depth empirical investigation into the long-tailed problem and found that pre-trained models with instance-balanced sampling already capture the well-learned representations for all classes; moreover, it is possible to achieve better long-tailed classification ability at low cost by only adjusting the classifier. Inspired by this observation, we propose a robust classifier with attentive relation routing, which assigns soft weights by automatically aggregating the relations. Extensive experiments on two datasets demonstrate the effectiveness of our proposed approach. Code and datasets are available in https://github.com/zjunlp/deepke.
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。
