Sparsity of formal knowledge and roughness of non-ontological construction make sparsity problem particularly prominent in Open Knowledge Graphs (OpenKGs). Due to sparse links, learning effective representation for few-shot entities becomes difficult. We hypothesize that by introducing negative samples, a contrastive learning (CL) formulation could be beneficial in such scenarios. However, existing CL methods model KG triplets as binary objects of entities ignoring the relation-guided ternary propagation patterns and they are too generic, i.e., they ignore zero-shot, few-shot and synonymity problems that appear in OpenKGs. To address this, we propose TernaryCL, a CL framework based on ternary propagation patterns among head, relation and tail. TernaryCL designs Contrastive Entity and Contrastive Relation to mine ternary discriminative features with both negative entities and relations, introduces Contrastive Self to help zero- and few-shot entities learn discriminative features, Contrastive Synonym to model synonymous entities, and Contrastive Fusion to aggregate graph features from multiple paths. Extensive experiments on benchmarks demonstrate the superiority of TernaryCL over state-of-the-art models.
翻译:正式知识的差别和非肿瘤建筑的粗度使得开放知识图(OpenKGs)中特别突出的问题更加突出。由于联系稀少,很难为少发实体学习有效的代表。我们假设,通过采用负面抽样,一种对比式学习(CL)的配方在这种情景中可能是有益的。然而,现有的CL方法模型KG三重(KG三重制)作为无视相关指导的代际传播模式的实体的二进制对象,它们过于普通,即它们忽略了OpenKGs(OpenKGs)中出现的零射、少射和共名问题。为了解决这个问题,我们提议TernararyCL,这是一个基于头部、关系和尾部之间长期传播模式的CL框架。TernCL设计差异性实体和与与与反面实体和关系中的地雷长期歧视特征的对比性关系,引入反向自自来帮助零和少发实体学习歧视特征,即它们忽略了在OpenKGGGs的模型中出现的零等同实体的对比性同性同性同性同性同性同性同性同性同性同性同性,以及从Treal-Clorental-Clornial-Climsurentsursurnial-sursurvial-sursursursursursursursursursursmalmal-sal-smationsymmmmmmmus。