QuanTaxo: A Quantum Approach to Self-Supervised Taxonomy Expansion

2025-01-23

AI Summary

Existing taxonomy classification systems suffer from low self-updating efficiency and difficulty in modeling lexical hierarchical polysemy. To address these challenges, this paper proposes a quantum-inspired taxonomy representation learning framework designed for dynamic knowledge graph evolution. It is the first to incorporate quantum superposition and interference principles into hierarchical structure modeling, explicitly encoding context-sensitive polysemy of entities in Hilbert space. The method integrates quantum-vector encoding, hierarchy-aware interference enhancement, self-supervised contrastive training, and a Wu & Palmer–compatible quantum similarity metric. Evaluated on four real-world benchmark datasets, it consistently outperforms eight classical embedding baselines: achieving +18.45% accuracy, +20.5% mean reciprocal rank (MRR), and +17.87% Wu & Palmer similarity. The framework significantly enhances both real-time taxonomy extensibility and semantic modeling fidelity.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Machine Learning: Quantum Machine Learning
• Data Mining & Knowledge Management: Semantic Web

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

A taxonomy is a hierarchical graph containing knowledge to provide valuable insights for various web applications. Online retail organizations like Microsoft and Amazon utilize taxonomies to improve product recommendations and optimize advertisement by enhancing query interpretation. However, the manual construction of taxonomies requires significant human effort. As web content continues to expand at an unprecedented pace, existing taxonomies risk becoming outdated, struggling to incorporate new and emerging information effectively. As a consequence, there is a growing need for dynamic taxonomy expansion to keep them relevant and up-to-date. Existing taxonomy expansion methods often rely on classical word embeddings to represent entities. However, these embeddings fall short in capturing hierarchical polysemy, where an entity's meaning can vary based on its position in the hierarchy and its surrounding context. To address this challenge, we introduce QuanTaxo, an innovative quantum-inspired framework for taxonomy expansion. QuanTaxo encodes entity representations in quantum space, effectively modeling hierarchical polysemy by leveraging the principles of Hilbert space to capture interference effects between entities, yielding richer and more nuanced representations. Comprehensive experiments on four real-world benchmark datasets show that QuanTaxo significantly outperforms classical embedding models, achieving substantial improvements of 18.45% in accuracy, 20.5% in Mean Reciprocal Rank, and 17.87% in Wu&Palmer metrics across eight classical embedding-based baselines. We further highlight the superiority of QuanTaxo through extensive ablation and case studies.

Problem

• Classification System
• Polysemy
• Knowledge Updating

Innovation

• Quantum-inspired Computing
• Semantic Polysemy Capture
• Automated Taxonomy Updating