arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.07524cs.LGcs.AI
收藏

用于归纳节点分类的神经结构预测

Neural Structured Prediction for Inductive Node Classification

Université de Montréal(蒙特利尔大学);Mila - Québec AI Institute(米拉-魁北克人工智能研究所);HEC Montréal(蒙特利尔高等商学院);Canadian Institute for Advanced Research (CIFAR)(加拿大高等研究院)

Meng Qu, Huiyu Cai, Jian Tang

摘要:

本文研究归纳环境下的节点分类,即,目的是在标记的训练图上学习一个模型,并将其推广到未标记的测试图上推断节点标签。这个问题已经通过学习有效的节点表示而用图神经网络(GNN)以及用于对节点标签的结构化输出进行建模的传统结构化预测方法(例如,条件随机场(CRF)。在本文中,我们提出了一种新的方法,称为结构化代理网络(SPN),它结合了这两个世界的优势。SPN定义了具有GNN的CRF的灵活潜在函数。然而,学习这样一个模型是不平凡的,因为它涉及到优化一个最大最小的游戏与高成本的推理。受马尔可夫网络定义的联合分布和边缘分布之间的潜在联系的启发,我们建议将优化问题的近似版本作为代理来解决,这会产生一个接近最优的解决方案,使学习更有效。在两个设置上的广泛实验表明,我们的方法优于许多竞争基线。

英文摘要:

This paper studies node classification in the inductive setting, i.e., aiming to learn a model on labeled training graphs and generalize it to infer node labels on unlabeled test graphs. This problem has been extensively studied with graph neural networks (GNNs) by learning effective node representations, as well as traditional structured prediction methods for modeling the structured output of node labels, e.g., conditional random fields (CRFs). In this paper, we present a new approach called the Structured Proxy Network (SPN), which combines the advantages of both worlds. SPN defines flexible potential functions of CRFs with GNNs. However, learning such a model is nontrivial as it involves optimizing a maximin game with high-cost inference. Inspired by the underlying connection between joint and marginal distributions defined by Markov networks, we propose to solve an approximate version of the optimization problem as a proxy, which yields a near-optimal solution, making learning more efficient. Extensive experiments on two settings show that our approach outperforms many competitive baselines.

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。

↑