Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs
This work provides a novel method for improving knowledge graph reasoning and anomaly detection, which is beneficial for applications like web search, e-commerce, and social networks, by better capturing hierarchical and semantic information.
This paper addresses the challenge of querying large and complex Knowledge Graphs (KGs) by formulating KG representation learning as a self-supervised logical query reasoning problem. The proposed Hyperboloid Embeddings (HypE) model learns entity and relation representations as hyperboloids in a Poincaré ball, significantly outperforming state-of-the-art results in KG reasoning on real-world datasets and demonstrating significant improvements in anomaly detection tasks.
Knowledge Graphs (KGs) are ubiquitous structures for information storagein several real-world applications such as web search, e-commerce, social networks, and biology. Querying KGs remains a foundational and challenging problem due to their size and complexity. Promising approaches to tackle this problem include embedding the KG units (e.g., entities and relations) in a Euclidean space such that the query embedding contains the information relevant to its results. These approaches, however, fail to capture the hierarchical nature and semantic information of the entities present in the graph. Additionally, most of these approaches only utilize multi-hop queries (that can be modeled by simple translation operations) to learn embeddings and ignore more complex operations such as intersection and union of simpler queries. To tackle such complex operations, in this paper, we formulate KG representation learning as a self-supervised logical query reasoning problem that utilizes translation, intersection and union queries over KGs. We propose Hyperboloid Embeddings (HypE), a novel self-supervised dynamic reasoning framework, that utilizes positive first-order existential queries on a KG to learn representations of its entities and relations as hyperboloids in a Poincaré ball. HypE models the positive first-order queries as geometrical translation, intersection, and union. For the problem of KG reasoning in real-world datasets, the proposed HypE model significantly outperforms the state-of-the art results. We also apply HypE to an anomaly detection task on a popular e-commerce website product taxonomy as well as hierarchically organized web articles and demonstrate significant performance improvements compared to existing baseline methods. Finally, we also visualize the learned HypE embeddings in a Poincaré ball to clearly interpret and comprehend the representation space.