Graph Component Contrastive Learning for Concept Relatedness Estimation
This addresses the problem of data scarcity and overlooked high-order relationships in concept relatedness estimation for AI and knowledge representation, representing a novel method for a known bottleneck.
The paper tackles concept relatedness estimation by formalizing its properties into a graph structure and introducing a Graph Component Contrastive Learning framework to capture high-order relationships, achieving significant improvements over state-of-the-art models on three datasets.
Concept relatedness estimation (CRE) aims to determine whether two given concepts are related. Existing methods only consider the pairwise relationship between concepts, while overlooking the higher-order relationship that could be encoded in a concept-level graph structure. We discover that this underlying graph satisfies a set of intrinsic properties of CRE, including reflexivity, commutativity, and transitivity. In this paper, we formalize the CRE properties and introduce a graph structure named ConcreteGraph. To address the data scarcity issue in CRE, we introduce a novel data augmentation approach to sample new concept pairs from the graph. As it is intractable for data augmentation to fully capture the structural information of the ConcreteGraph due to a large amount of potential concept pairs, we further introduce a novel Graph Component Contrastive Learning framework to implicitly learn the complete structure of the ConcreteGraph. Empirical results on three datasets show significant improvement over the state-of-the-art model. Detailed ablation studies demonstrate that our proposed approach can effectively capture the high-order relationship among concepts.