EASC: An exception-aware semantic compression framework for real-world knowledge graphs

Abstract

Knowledge graphs (KGs) have achieved great success in many real applications, and great efforts have been dedicated to constructing larger knowledge graphs. An obvious trend in KG construction is that the KGs become ever-increasingly bigger. However, we argue that constructing a KG by directly inserting more triples may harm the performance of the KG, and one possible solution is KG compression. In this paper, we propose an exception-aware semantic lossless compression framework EASC to compress a KG. Since many triples can be inferred from other triples with semantic rules, we remove the triples that can be inferred and store the rules and exception cases. Specifically, we formalize the lossless compression problem as a weighted set cover problem, which is NP-hard, and propose a semantic lossless compression algorithm to get an approximation result. We conduct extensive experiments on seven real-world large-scale KGs. The results show that EASC achieves state-of-the-art performance in semantic compression methods. Furthermore, by combining EASC as an independent module with syntactic compression methods, we achieve state-of-the-art performance in lossless compression methods.