# Context-aware Entity Typing in Knowledge Graphs

arXiv: https://arxiv.org/abs/2109.07990 · HTML: https://mlsanity.com/paper/2109.07990/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 16 Sep 2021.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Holographic Embeddings of Knowledge Graphs](https://mlsanity.com/paper/1510.04935/) (2015)
- [Canonical Tensor Decomposition for Knowledge Base Completion](https://mlsanity.com/paper/1806.07297/) (2018)
- [Ultra-Fine Entity Typing](https://mlsanity.com/paper/1807.04905/) (2018)
- [DGL-KE: Training Knowledge Graph Embeddings at Scale](https://mlsanity.com/paper/2004.08532/) (2020)
- [Question Answering with Subgraph Embeddings](https://mlsanity.com/paper/1406.3676/) (2014)
- [Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts](https://mlsanity.com/paper/2103.08115/) (2021)
- [Differentiating Concepts and Instances for Knowledge Graph Embedding](https://mlsanity.com/paper/1811.04588/) (2018)
- [Refining activation downsampling with SoftPool](https://mlsanity.com/paper/2101.00440/) (2021)
- [Zero-Shot Open Entity Typing as Type-Compatible Grounding](https://mlsanity.com/paper/1907.03228/) (2019)
- [Connecting Embeddings for Knowledge Graph Entity Typing](https://mlsanity.com/paper/2007.10873/) (2020)
- [Inferring Missing Entity Type Instances for Knowledge Base Completion: New Dataset and Methods](https://mlsanity.com/paper/1504.06658/) (2015)

## Built on by (most cited first, 12 of 12)

- [Improving Personality Consistency in Conversation by Persona Extending](https://mlsanity.com/paper/2208.10816/) (2022)
- [Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2205.00782/) (2022)
- [Transformer-based Entity Typing in Knowledge Graphs](https://mlsanity.com/paper/2210.11151/) (2022)
- [The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing](https://mlsanity.com/paper/2404.08313/) (2024)
- [HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold](https://mlsanity.com/paper/2210.08806/) (2022)
- [AsyncET: Asynchronous Learning for Knowledge Graph Entity Typing with Auxiliary Relations](https://mlsanity.com/paper/2308.16055/) (2023)
- [Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs](https://mlsanity.com/paper/2310.12008/) (2023)
- [HyperMono: A Monotonicity-aware Approach to Hyper-Relational Knowledge Representation](https://mlsanity.com/paper/2404.09848/) (2024)
- [Multi-level Matching Network for Multimodal Entity Linking](https://mlsanity.com/paper/2412.10440/) (2024)
- [Markov Process-Based Graph Convolutional Networks for Entity Classification in Knowledge Graphs](https://mlsanity.com/paper/2412.17438/) (2024)
- [Type-based Neural Link Prediction Adapter for Complex Query Answering](https://mlsanity.com/paper/2401.16045/) (2024)
- [COTET: Cross-view Optimal Transport for Knowledge Graph Entity Typing](https://mlsanity.com/paper/2405.13602/) (2024)

## Abstract (arXiv)

Knowledge graph entity typing aims to infer entities' missing types in knowledge graphs which is an important but under-explored issue. This paper proposes a novel method for this task by utilizing entities' contextual information. Specifically, we design two inference mechanisms: i) N2T: independently use each neighbor of an entity to infer its type; ii) Agg2T: aggregate the neighbors of an entity to infer its type. Those mechanisms will produce multiple inference results, and an exponentially weighted pooling method is used to generate the final inference result. Furthermore, we propose a novel loss function to alleviate the false-negative problem during training. Experiments on two real-world KGs demonstrate the effectiveness of our method. The source code and data of this paper can be obtained from https://github.com/CCIIPLab/CET.