Disentangled Ontology Embedding for Zero-shot Learning

TL;DR

This paper introduces a novel approach for zero-shot learning that leverages disentangled ontology embeddings to better capture complex inter-class relationships, improving performance across multiple benchmarks.

Contribution

It proposes a new disentangled ontology embedding method guided by ontology properties and a ZSL framework with two solutions, enhancing the utilization of class relationships.

Findings

Outperforms state-of-the-art methods on five benchmarks

Effective in zero-shot image classification and KG completion

Validated by ablation and case studies

Abstract

Knowledge Graph (KG) and its variant of ontology have been widely used for knowledge representation, and have shown to be quite effective in augmenting Zero-shot Learning (ZSL). However, existing ZSL methods that utilize KGs all neglect the intrinsic complexity of inter-class relationships represented in KGs. One typical feature is that a class is often related to other classes in different semantic aspects. In this paper, we focus on ontologies for augmenting ZSL, and propose to learn disentangled ontology embeddings guided by ontology properties to capture and utilize more fine-grained class relationships in different aspects. We also contribute a new ZSL framework named DOZSL, which contains two new ZSL solutions based on generative models and graph propagation models, respectively, for effectively utilizing the disentangled ontology embeddings. Extensive evaluations have been conducted on five benchmarks across zero-shot image classification (ZS-IMGC) and zero-shot KG completion (ZS-KGC). DOZSL often achieves better performance than the state-of-the-art, and its components have been verified by ablation studies and case studies. Our codes and datasets are available at https://github.com/zjukg/DOZSL.