InGram: Inductive Knowledge Graph Embedding via Relation Graphs
This addresses a key limitation in real-world knowledge graphs where new entities often come with new relations, making it significant for applications like recommendation systems and semantic web, though it is an incremental improvement over existing inductive methods.
The paper tackles the problem of inductive knowledge graph completion where new entities and relations appear at inference time, proposing InGram which generates embeddings for both, and it outperforms 14 state-of-the-art methods in varied scenarios.
Inductive knowledge graph completion has been considered as the task of predicting missing triplets between new entities that are not observed during training. While most inductive knowledge graph completion methods assume that all entities can be new, they do not allow new relations to appear at inference time. This restriction prohibits the existing methods from appropriately handling real-world knowledge graphs where new entities accompany new relations. In this paper, we propose an INductive knowledge GRAph eMbedding method, InGram, that can generate embeddings of new relations as well as new entities at inference time. Given a knowledge graph, we define a relation graph as a weighted graph consisting of relations and the affinity weights between them. Based on the relation graph and the original knowledge graph, InGram learns how to aggregate neighboring embeddings to generate relation and entity embeddings using an attention mechanism. Experimental results show that InGram outperforms 14 different state-of-the-art methods on varied inductive learning scenarios.