Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction

By Zhanqiu Zhang, Jianyu Cai, Yongdong Zhang, Jie Wang. AAAI Conference on Artificial Intelligence, 2019

501 citations recorded by the source corpus.

Knowledge graph embedding, which aims to represent entities and relations as low dimensional vectors (or matrices, tensors, etc.), has been shown to be a powerful technique for predicting missing links in knowledge graphs. Existing knowledge graph embedding models mainly focus on modeling relation patterns such as symmetry/antisymmetry, inversion, and composition. However, many existing approaches fail to model semantic hierarchies, which are common in real-world applications. To address this challenge, we propose a novel knowledge graph embedding model—namely, Hierarchy-Aware Knowledge Graph Embedding (HAKE)—which maps entities into the polar coordinate system. HAKE is inspired by the fact that concentric circles in the polar coordinate system can naturally reflect the hierarchy. Specifically, the radial coordinate aims to model entities at different levels of the hierarchy, and entities with smaller radii are expected to be at higher levels; the angular coordinate aims to distinguish entities at the same level of the hierarchy, and these entities are expected to have roughly the same radii but different angles. Experiments demonstrate that HAKE can effectively model the semantic hierarchies in knowledge graphs, and significantly outperforms existing state-of-the-art methods on benchmark datasets for the link prediction task.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/81e82158510edb72680a9a832df970d2743d9a63

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Shirui Pan
3. Erik Cambria
4. Hinrich Schütze
5. Nora Kassner
6. Feng Xia
7. Zhaocheng Zhu
8. Jian Tang

In Management Science and Operations Research

1. Philip S. Yu
2. Shirui Pan
3. Yue Liu
4. Siwei Wang
5. Lingyuan Meng
6. Wenxuan Tu
7. Hinrich Schütze
8. Jian Tang

Citations in the corpus

• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction (2021, background): “Results of RotatE, HAKE and LowFER are taken from their original papers [52, 76, 1].”
• Knowledge Graph Embedding for Link Prediction (2020, methodology): “In both experiments, we report results for the three best-performing models of each family, that is, ComplEx [67] for bilinear family, HAKE [81] for the geometric family, and [69] for the Deep Learning family; we use the same hyperparameters and number of training epochs in each training process.”
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “Meanwhile, HAKE [34] models the semantic hierarchy rather than relation patterns based on the polar coordinate space, which can naturally reflect the hierarchy.”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, methodology): “imensions by a bilinear tensor neural layer. The relational interaction between head and tail hTcMt is captured as a tensor denoted as Mc2R d k. Instead of using the Cartesian coordinate system, HAKE [18] captures semantic hierarchies by mapping entities into the polar coordinate system, i.e., entit”
• Are Pretrained Language Models Symbolic Reasoners over Knowledge? (2020, background): “In the knowledge base domain, prior work (Sun et al., 2019; Zhang et al., 2020) has shown that models that are able to learn symbolic rules are superior to ones that are not.”
• Knowledge Graphs: Opportunities and Challenges (2023, background): “For instance, Zhang et al. (2020a) presented a Health Knowledge Graph Builder (HKGB) to build medical knowledge graphs with clinicians’ expertise.”