Resilience in Knowledge Graph Embeddings
Not on the map. Why?
Abstract (arXiv)
In recent years, knowledge graphs have gained interest and witnessed widespread applications in various domains, such as information retrieval, question-answering, recommendation systems, amongst others. Large-scale knowledge graphs to this end have demonstrated their utility in effectively representing structured knowledge. To further facilitate the application of machine learning techniques, knowledge graph embedding (KGE) models have been developed. Such models can transform entities and relationships within knowledge graphs into vectors. However, these embedding models often face challenges related to noise, missing information, distribution shift, adversarial attacks, etc. This can lead to sub-optimal embeddings and incorrect inferences, thereby negatively impacting downstream applications. While the existing literature has focused so far on adversarial attacks on KGE models, the challenges related to the other critical aspects remain unexplored. In this paper, we, first of all, give a unified definition of resilience, encompassing several factors such as generalisation, performance consistency, distribution adaption, and robustness. After formalizing these concepts for machine learning in general, we define them in the context of knowledge graphs. To find the gap in the existing works on resilience in the context of knowledge graphs, we perform a systematic survey, taking into account all these aspects mentioned previously. Our survey results show that most of the existing works focus on a specific aspect of resilience, namely robustness. After categorizing such works based on their respective aspects of resilience, we discuss the challenges and future research directions.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 55 of its 137 references that are in the map. First posted on arXiv 28 Oct 2024.
Builds on
55 of 137 references.
References · 55
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
- 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
- 2016Complex Embeddings for Simple Link Predictioncited by 897
- 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
- 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
- 2020Knowledge Graphscited by 619
- 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
- 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
38 more
- 2020Weight Poisoning Attacks on Pre-trained Modelscited by 318
- 2020Low-Dimensional Hyperbolic Knowledge Graph Embeddingscited by 195
- 2019Quaternion Knowledge Graph Embeddingscited by 175
- 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
- 2013Learning by Transductioncited by 120
- 2020A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphscited by 119
- 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
- 2020Deep Visual Domain Adaptationcited by 91
- 2019Multi-Channel Graph Neural Network for Entity Alignmentcited by 86
- 2023Large Language Models and Knowledge Graphs: Opportunities and Challengescited by 71
- 2019Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendationcited by 70
- 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 69
- 2022Knowledge Graph Contrastive Learning for Recommendationcited by 69
- 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
- 2017KBGAN: Adversarial Learning for Knowledge Graph Embeddingscited by 62
- 2021Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bitscited by 49
- 2018Hypernetwork Knowledge Graph Embeddingscited by 38
- 2019Data Poisoning Attack against Knowledge Graph Embeddingcited by 34
- 2020Class-Weighted Classification: Trade-offs and Robust Approachescited by 30
- 2018Embedding Uncertain Knowledge Graphscited by 25
- 2019Investigating Robustness and Interpretability of Link Prediction via Adversarial Modificationscited by 25
- 2016Lifted Rule Injection for Relation Embeddingscited by 22
- 2023Neural Compositional Rule Learning for Knowledge Graph Reasoningcited by 20
- 2021DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Networkcited by 19
- 2022A Survey of Neural Trojan Attacks and Defenses in Deep Learningcited by 17
- 2021Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methodscited by 16
- 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
- 2021Convolutional Hypercomplex Embeddings for Link Predictioncited by 15
- 2017Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidencecited by 14
- 2023A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospectscited by 14
- 2021Poisoning Knowledge Graph Embeddings via Relation Inference Patternscited by 12
- 2022Spectral Adversarial Training for Robust Graph Neural Networkcited by 12
- 2021Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustnesscited by 9
- 2024Predictive Multiplicity of Knowledge Graph Embeddings in Link Predictioncited by 9
- 2022A Review of Knowledge Graph Completioncited by 8
- 2023On the Security Risks of Knowledge Graph Reasoningcited by 5
- 2023Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shiftcited by 5
- 2024Conformalized Answer Set Prediction for Knowledge Graph Embeddingcited by 5
50 most cited of 55 All 55 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.