Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?

by   Anson Bastos, et al.
Association for Computing Machinery
Indian Institute of Technology Hyderabad

In this paper we present a novel method, Knowledge Persistence (𝒦𝒫), for faster evaluation of Knowledge Graph (KG) completion approaches. Current ranking-based evaluation is quadratic in the size of the KG, leading to long evaluation times and consequently a high carbon footprint. 𝒦𝒫 addresses this by representing the topology of the KG completion methods through the lens of topological data analysis, concretely using persistent homology. The characteristics of persistent homology allow 𝒦𝒫 to evaluate the quality of the KG completion looking only at a fraction of the data. Experimental results on standard datasets show that the proposed metric is highly correlated with ranking metrics (Hits@N, MR, MRR). Performance evaluation shows that 𝒦𝒫 is computationally efficient: In some cases, the evaluation time (validation+test) of a KG completion method has been reduced from 18 hours (using Hits@10) to 27 seconds (using 𝒦𝒫), and on average (across methods data) reduces the evaluation time (validation+test) by ≈ 99.96%.


page 1

page 2

page 3

page 4


Triple Classification for Scholarly Knowledge Graph Completion

Scholarly Knowledge Graphs (KGs) provide a rich source of structured inf...

A Temporal Knowledge Graph Completion Method Based on Balanced Timestamp Distribution

Completion through the embedding representation of the knowledge graph (...

Model-based Subsampling for Knowledge Graph Completion

Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing...

Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network

Knowledge Graph (KG) completion research usually focuses on densely conn...

Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective

Knowledge graph completion (KGC) aims to infer missing knowledge triples...

Topology-Driven Generative Completion of Lacunae in Molecular Data

We introduce an approach to the targeted completion of lacunae in molecu...

Validation and Topic-driven Ranking for Biomedical Hypothesis Generation Systems

Literature underpins research, providing the foundation for new ideas. B...

Please sign up or login with your details

Forgot password? Click here to reset