LGCLIRApr 22, 2021

Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding

arXiv:2104.10880v117 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of improving knowledge graph embedding for AI applications, but it is incremental as it builds on existing AutoML techniques.

The paper tackled the problem of designing effective scoring functions for knowledge graph embedding by searching relation-aware functions, achieving better performance than state-of-the-art methods on benchmark datasets.

The scoring function, which measures the plausibility of triplets in knowledge graphs (KGs), is the key to ensure the excellent performance of KG embedding, and its design is also an important problem in the literature. Automated machine learning (AutoML) techniques have recently been introduced into KG to design task-aware scoring functions, which achieve state-of-the-art performance in KG embedding. However, the effectiveness of searched scoring functions is still not as good as desired. In this paper, observing that existing scoring functions can exhibit distinct performance on different semantic patterns, we are motivated to explore such semantics by searching relation-aware scoring functions. But the relation-aware search requires a much larger search space than the previous one. Hence, we propose to encode the space as a supernet and propose an efficient alternative minimization algorithm to search through the supernet in a one-shot manner. Finally, experimental results on benchmark datasets demonstrate that the proposed method can efficiently search relation-aware scoring functions, and achieve better embedding performance than state-of-the-art methods.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes