提出可处理大规模知识图谱的归纳式逻辑多跳问答方法
InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs
- 基于小波变换构建归纳式嵌入，支持训练外实体推理
- 仅需一半消息传递层数，性能优于主流模型75%场景
- 适用于超大规模知识图谱，如Wiki-KG
知识图谱上的逻辑多跳查询可视为在隐含完备性假设下的查询问题。现有工作主要关注存在量词一阶逻辑（EFO）查询，包含合取、析取和否定运算。多数方法采用传导式推理，无法处理训练时未见的实体。现实世界中资源有限，无法用大型知识图谱的所有节点进行训练。为此，我们提出InductWave，一种基于小波变换的归纳式嵌入方法，用于大规模知识图谱的逻辑查询。训练图节点少于测试图，模型性能与基线相当，但仅需一半消息传递层数，在多数情况下表现更优，达75%的实验场景。更低的资源需求使其可在大规模图上评估，如Wiki-KG。我们在FB15k-(237)数据集上通过不同训练-测试比例的大量实验验证，结果优于当前最优模型。代码与数据集见https://github.com/kracr/inductwave/。
原文摘要 · Abstract (English)
Logical Multi-Hop Query Answering over Knowledge Graphs (KGs) can be formulated as querying, with an implicit completeness assumption. Current works mainly focus on Existential First Order Logic (EFO) queries. These EFO queries contain conjunction, disjunction, and negation operators. Most existing works employ transductive reasoning, meaning they are not capable of reasoning over entities unseen during training. In the real world, there is a resource scarcity, and we cannot train a model with all the nodes of a large KG. Hence, we propose InductWave, a wavelet-based inductive embedding method for logical query answering on large KGs. Here, the training graph consists of fewer nodes than the test graph. Our model performs on par with the baseline models while having half the number of message-passing layers. It outperforms all of them in most cases, with 75% of the layers. These fewer resource requirements enable us to evaluate InductWave on massive graphs, such as Wiki-KG. We test our model using extensive experiments across varying train-test graph proportions of the FB15k-(237) dataset, comparing it with the state-of-the-art models. The code and datasets for the model are available at https://github.com/kracr/inductwave/.
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。