UniKG: A Benchmark and Universal Embedding for Large-Scale Knowledge Graphs

TL;DR

This paper introduces UniKG, a large-scale heterogeneous graph dataset from Wikidata, along with novel learning strategies including semantic alignment and anisotropy propagation to improve knowledge graph embedding and node classification.

Contribution

The paper constructs the largest heterogeneous graph benchmark UniKG and proposes two innovative methods for effective large-scale heterogeneous graph learning.

Findings

UniKG contains over 77 million entities and 2000 association types.

The proposed methods improve multi-hop information propagation in large-scale HGs.

Baseline evaluations demonstrate the effectiveness of the new strategies.

Abstract

Irregular data in real-world are usually organized as heterogeneous graphs (HGs) consisting of multiple types of nodes and edges. To explore useful knowledge from real-world data, both the large-scale encyclopedic HG datasets and corresponding effective learning methods are crucial, but haven't been well investigated. In this paper, we construct a large-scale HG benchmark dataset named UniKG from Wikidata to facilitate knowledge mining and heterogeneous graph representation learning. Overall, UniKG contains more than 77 million multi-attribute entities and 2000 diverse association types, which significantly surpasses the scale of existing HG datasets. To perform effective learning on the large-scale UniKG, two key measures are taken, including (i) the semantic alignment strategy for multi-attribute entities, which projects the feature description of multi-attribute nodes into a common embedding space to facilitate node aggregation in a large receptive field; (ii) proposing a novel plug-and-play anisotropy propagation module (APM) to learn effective multi-hop anisotropy propagation kernels, which extends methods of large-scale homogeneous graphs to heterogeneous graphs. These two strategies enable efficient information propagation among a tremendous number of multi-attribute entities and meantimes adaptively mine multi-attribute association through the multi-hop aggregation in large-scale HGs. We set up a node classification task on our UniKG dataset, and evaluate multiple baseline methods which are constructed by embedding our APM into large-scale homogenous graph learning methods. Our UniKG dataset and the baseline codes have been released at https://github.com/Yide-Qiu/UniKG.