TIEG-Youpu Solution for NeurIPS 2022 WikiKG90Mv2-LSC

TL;DR

This paper presents TIEG-Youpu, a novel scalable knowledge graph embedding method for WikiKG90Mv2, improving retrieval and re-ranking stages to enhance link prediction accuracy on large-scale data.

Contribution

It introduces a priority infilling retrieval model and an ensemble re-ranking approach with neighbor-enhanced representations for large-scale knowledge graph embedding.

Findings

Outperforms baseline methods in link prediction accuracy.

Improves validation set MRR from 0.2342 to 0.2839.

Effective for large-scale knowledge graphs like WikiKG90Mv2.

Abstract

WikiKG90Mv2 in NeurIPS 2022 is a large encyclopedic knowledge graph. Embedding knowledge graphs into continuous vector spaces is important for many practical applications, such as knowledge acquisition, question answering, and recommendation systems. Compared to existing knowledge graphs, WikiKG90Mv2 is a large scale knowledge graph, which is composed of more than 90 millions of entities. Both efficiency and accuracy should be considered when building graph embedding models for knowledge graph at scale. To this end, we follow the retrieve then re-rank pipeline, and make novel modifications in both retrieval and re-ranking stage. Specifically, we propose a priority infilling retrieval model to obtain candidates that are structurally and semantically similar. Then we propose an ensemble based re-ranking model with neighbor enhanced representations to produce final link prediction results among retrieved candidates. Experimental results show that our proposed method outperforms existing baseline methods and improves MRR of validation set from 0.2342 to 0.2839.