To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
This work addresses a specific bottleneck in knowledge graph completion for AI applications, offering an incremental improvement over existing embedding methods.
The paper tackles the problem of knowledge graph completion by addressing the difficulty of predicting links between distant entity pairs due to unreliable implicit memorization of multi-hop relation rules in embedding models, and it introduces a Vertical Learning Paradigm (VLP) that explicitly copies target information from related triples, resulting in improved generalization and easier distant link prediction, with experiments validating the approach on two standard benchmarks.
Embedding models have shown great power in knowledge graph completion (KGC) task. By learning structural constraints for each training triple, these methods implicitly memorize intrinsic relation rules to infer missing links. However, this paper points out that the multi-hop relation rules are hard to be reliably memorized due to the inherent deficiencies of such implicit memorization strategy, making embedding models underperform in predicting links between distant entity pairs. To alleviate this problem, we present Vertical Learning Paradigm (VLP), which extends embedding models by allowing to explicitly copy target information from related factual triples for more accurate prediction. Rather than solely relying on the implicit memory, VLP directly provides additional cues to improve the generalization ability of embedding models, especially making the distant link prediction significantly easier. Moreover, we also propose a novel relative distance based negative sampling technique (ReD) for more effective optimization. Experiments demonstrate the validity and generality of our proposals on two standard benchmarks. Our code is available at https://github.com/rui9812/VLP.