论文标题
魔鬼是分类器：通过解耦分析研究长尾巴关系分类
The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis
论文作者
论文摘要
长尾关系分类是一个具有挑战性的问题，因为头等阶层可能主导训练阶段，从而导致尾部性能恶化。现有的解决方案通常通过类平衡策略来解决此问题，例如数据重新采样和损失重新加权，但是所有这些方法都遵循了对代表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研究，发现具有实例平衡抽样的预培训模型已经捕获了所有类别的良好代表。此外，仅通过调整分类器，就可以以低成本获得更好的长尾分类能力。受到这一观察的启发，我们提出了一个具有细心关系路由的强大分类器，该分类器通过自动汇总关系来分配软权重。在两个数据集上进行的广泛实验证明了我们提出的方法的有效性。代码和数据集可在https://github.com/zjunlp/deepke中找到。
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.
