Abstract
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, which contain conjunction, disjunction, and negation operators. Most existing works employ transductive reasoning, meaning they cannot reason 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. Therefore, 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 baseline models while having half the number of message-passing layers. It outperforms all of them in most cases, using only 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 state-of-the-art models. The code and datasets for the model are available at GitHub.
Blogger's Review: InductWave introduces a wavelet-based approach to enhance inductive reasoning in query answering over knowledge graphs, achieving efficiency with reduced resource consumption. This innovation opens up new potentials for knowledge graph applications at scale, raising interesting questions about optimizing methods for more complex queries in the future.