用马尔可夫过程改进GCN，提升知识图谱实体分类准确率
Markov Process-Based Graph Convolutional Networks for Entity Classification in Knowledge Graphs
- 将马尔可夫过程融入GCN，动态学习推理步数
- 在多个数据集上优于现有模型，提升分类性能
- 可调节计算步数，兼顾效率与精度，适合复杂分类任务
尽管知识图谱（KGs）蕴含大量信息，但实体的类别归属往往不完整。图卷积网络（GCNs）已被证明能有效预测实体的类别归属，但这些模型未能充分捕捉任务的复杂性，影响了预测能力。为此，本文将基于马尔可夫过程的架构引入经典GCN中，构建端到端网络，在马尔可夫过程中学习实体类别归属的预测。计算步数通过训练时的几何分布自动学习。损失函数结合了证据学习领域的思想。实验表明，在多个架构和数据集上，该方法均优于现有模型。根据几何分布超参数的选择，可调整预期计算步数，从而在训练中提升效率与准确性。
原文摘要 · Abstract (English)
Despite the vast amount of information encoded in Knowledge Graphs (KGs), information about the class affiliation of entities remains often incomplete. Graph Convolutional Networks (GCNs) have been shown to be effective predictors of complete information about the class affiliation of entities in KGs. However, these models do not learn the class affiliation of entities in KGs incorporating the complexity of the task, which negatively affects the models prediction capabilities. To address this problem, we introduce a Markov process-based architecture into well-known GCN architectures. This end-to-end network learns the prediction of class affiliation of entities in KGs within a Markov process. The number of computational steps is learned during training using a geometric distribution. At the same time, the loss function combines insights from the field of evidential learning. The experiments show a performance improvement over existing models in several studied architectures and datasets. Based on the chosen hyperparameters for the geometric distribution, the expected number of computation steps can be adjusted to improve efficiency and accuracy during training.
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。