# AsyncET: Asynchronous Learning for Knowledge Graph Entity Typing with Auxiliary Relations

arXiv: https://arxiv.org/abs/2308.16055 · HTML: https://mlsanity.com/paper/2308.16055/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 30 Aug 2023.

## Builds on (most cited first, 19 of 19)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs](https://mlsanity.com/paper/1906.01195/) (2019)
- [Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts](https://mlsanity.com/paper/2103.08115/) (2021)
- [Green Learning: Introduction, Examples and Outlook](https://mlsanity.com/paper/2210.00965/) (2022)
- [Differentiating Concepts and Instances for Knowledge Graph Embedding](https://mlsanity.com/paper/1811.04588/) (2018)
- [OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding](https://mlsanity.com/paper/2105.07688/) (2021)
- [Connecting Embeddings for Knowledge Graph Entity Typing](https://mlsanity.com/paper/2007.10873/) (2020)
- [Noise Mitigation for Neural Entity Typing and Relation Extraction](https://mlsanity.com/paper/1612.07495/) (2016)
- [Transformer-based Entity Typing in Knowledge Graphs](https://mlsanity.com/paper/2210.11151/) (2022)
- [WGCN: Graph Convolutional Networks with Weighted Structural Features](https://mlsanity.com/paper/2104.14060/) (2021)
- [Context-aware Entity Typing in Knowledge Graphs](https://mlsanity.com/paper/2109.07990/) (2021)
- [CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding](https://mlsanity.com/paper/2112.10067/) (2021)
- [CompoundE: Knowledge Graph Embedding with Translation, Rotation and Scaling Compound Operations](https://mlsanity.com/paper/2207.05324/) (2022)
- [Corpus-level Fine-grained Entity Typing Using Contextual Information](https://mlsanity.com/paper/1606.07901/) (2016)

## Built on by (most cited first, 2 of 2)

- [Time Sensitive Knowledge Editing through Efficient Finetuning](https://mlsanity.com/paper/2406.04496/) (2024)
- [Knowledge Graph Embedding: An Overview](https://mlsanity.com/paper/2309.12501/) (2023)

## Abstract (arXiv)

Knowledge graph entity typing (KGET) is a task to predict the missing entity types in knowledge graphs (KG). Previously, KG embedding (KGE) methods tried to solve the KGET task by introducing an auxiliary relation, 'hasType', to model the relationship between entities and their types. However, a single auxiliary relation has limited expressiveness for diverse entity-type patterns. We improve the expressiveness of KGE methods by introducing multiple auxiliary relations in this work. Similar entity types are grouped to reduce the number of auxiliary relations and improve their capability to model entity-type patterns with different granularities. With the presence of multiple auxiliary relations, we propose a method adopting an Asynchronous learning scheme for Entity Typing, named AsyncET, which updates the entity and type embeddings alternatively to keep the learned entity embedding up-to-date and informative for entity type prediction. Experiments are conducted on two commonly used KGET datasets to show that the performance of KGE methods on the KGET task can be substantially improved by the proposed multiple auxiliary relations and asynchronous embedding learning. Furthermore, our method has a significant advantage over state-of-the-art methods in model sizes and time complexity.