Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learning

by   Qian Li, et al.
Northeastern University
Nanyang Technological University

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.


KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion

Knowledge Graph Embeddings (KGE) aim to map entities and relations to lo...

Structure Aware Negative Sampling in Knowledge Graphs

Learning low-dimensional representations for entities and relations in k...

Relational Symmetry based Knowledge Graph Contrastive Learning

Knowledge graph embedding (KGE) aims to learn powerful representations t...

ZeroKBC: A Comprehensive Benchmark for Zero-Shot Knowledge Base Completion

Knowledge base completion (KBC) aims to predict the missing links in kno...

Representation Learning for Visual-Relational Knowledge Graphs

A visual-relational knowledge graph (KG) is a KG whose entities are asso...

Leveraging Knowledge Graphs for Zero-Shot Object-agnostic State Classification

We investigate the problem of Object State Classification (OSC) as a zer...

Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning

Relational graph neural networks have garnered particular attention to e...

Please sign up or login with your details

Forgot password? Click here to reset