# Contrastive Knowledge Graph Error Detection

arXiv: https://arxiv.org/abs/2211.10030 · HTML: https://mlsanity.com/paper/2211.10030/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 18 Nov 2022.

## Builds on (most cited first, 26 of 26)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [Graph Representation Learning via Graphical Mutual Information Maximization](https://mlsanity.com/paper/2002.01169/) (2020)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs](https://mlsanity.com/paper/1906.01195/) (2019)
- [Knowledge Graph Convolutional Networks for Recommender Systems](https://mlsanity.com/paper/1904.12575/) (2019)
- [Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation](https://mlsanity.com/paper/2012.06852/) (2020)
- [Contrastive Self-supervised Learning for Graph Classification](https://mlsanity.com/paper/2009.05923/) (2020)
- [Knowledge Graph Embedding with Iterative Guidance from Soft Rules](https://mlsanity.com/paper/1711.11231/) (2017)
- [Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction](https://mlsanity.com/paper/2010.11711/) (2020)
- [Discriminative Predicate Path Mining for Fact Checking in Knowledge Graphs](https://mlsanity.com/paper/1510.05911/) (2015)
- [Triple Trustworthiness Measurement for Knowledge Graph](https://mlsanity.com/paper/1809.09414/) (2018)
- [Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence](https://mlsanity.com/paper/1705.03202/) (2017)
- [Novelty Detection via Contrastive Learning with Negative Data Augmentation](https://mlsanity.com/paper/2106.09958/) (2021)
- [What is Normal, What is Strange, and What is Missing in a Knowledge Graph: Unified Characterization via Inductive Summarization](https://mlsanity.com/paper/2003.10412/) (2020)
- [KGClean: An Embedding Powered Knowledge Graph Cleaning Framework](https://mlsanity.com/paper/2004.14478/) (2020)
- [Efficient Knowledge Graph Validation via Cross-Graph Representation Learning](https://mlsanity.com/paper/2008.06995/) (2020)
- [SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement](https://mlsanity.com/paper/1902.06377/) (2019)

## Built on by (most cited first, 11 of 11)

- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [KnowGPT: Knowledge Graph based Prompting for Large Language Models](https://mlsanity.com/paper/2312.06185/) (2023)
- [Neuro-Symbolic Entity Alignment via Variational Inference](https://mlsanity.com/paper/2410.04153/) (2024)
- [AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction](https://mlsanity.com/paper/2510.15339/) (2025)
- [Logical Reasoning with Relation Network for Inductive Knowledge Graph Completion](https://mlsanity.com/paper/2406.01140/) (2024)
- [Promoting Fairness in Link Prediction with Graph Enhancement](https://mlsanity.com/paper/2409.08658/) (2024)
- [TinyGraph: Joint Feature and Node Condensation for Graph Neural Networks](https://mlsanity.com/paper/2407.08064/) (2024)
- [Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs](https://mlsanity.com/paper/2501.15791/) (2025)
- [Knowledge Graph Pruning for Recommendation](https://mlsanity.com/paper/2405.11531/) (2024)
- [Conflict Detection for Temporal Knowledge Graphs:A Fast Constraint Mining Algorithm and New Benchmarks](https://mlsanity.com/paper/2312.11053/) (2023)
- [Type Information-Assisted Self-Supervised Knowledge Graph Denoising](https://mlsanity.com/paper/2503.09916/) (2025)

## Abstract (arXiv)

Knowledge Graph (KG) errors introduce non-negligible noise, severely affecting KG-related downstream tasks. Detecting errors in KGs is challenging since the patterns of errors are unknown and diverse, while ground-truth labels are rare or even unavailable. A traditional solution is to construct logical rules to verify triples, but it is not generalizable since different KGs have distinct rules with domain knowledge involved. Recent studies focus on designing tailored detectors or ranking triples based on KG embedding loss. However, they all rely on negative samples for training, which are generated by randomly replacing the head or tail entity of existing triples. Such a negative sampling strategy is not enough for prototyping practical KG errors, e.g., (Bruce_Lee, place_of_birth, China), in which the three elements are often relevant, although mismatched. We desire a more effective unsupervised learning mechanism tailored for KG error detection. To this end, we propose a novel framework - ContrAstive knowledge Graph Error Detection (CAGED). It introduces contrastive learning into KG learning and provides a novel way of modeling KG. Instead of following the traditional setting, i.e., considering entities as nodes and relations as semantic edges, CAGED augments a KG into different hyper-views, by regarding each relational triple as a node. After joint training with KG embedding and contrastive learning loss, CAGED assesses the trustworthiness of each triple based on two learning signals, i.e., the consistency of triple representations across multi-views and the self-consistency within the triple. Extensive experiments on three real-world KGs show that CAGED outperforms state-of-the-art methods in KG error detection. Our codes and datasets are available at https://github.com/Qing145/CAGED.git.