# Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attacks

arXiv: https://arxiv.org/abs/2407.06855 · HTML: https://mlsanity.com/paper/2407.06855/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 27 of 27)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [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)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [Low-Dimensional Hyperbolic Knowledge Graph Embeddings](https://mlsanity.com/paper/2005.00545/) (2020)
- [Quaternion Knowledge Graph Embeddings](https://mlsanity.com/paper/1904.10281/) (2019)
- [A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network](https://mlsanity.com/paper/1712.02121/) (2017)
- [Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits](https://mlsanity.com/paper/2102.10496/) (2021)
- [Hypernetwork Knowledge Graph Embeddings](https://mlsanity.com/paper/1808.07018/) (2018)
- [Data Poisoning Attack against Knowledge Graph Embedding](https://mlsanity.com/paper/1904.12052/) (2019)
- [Explicit Regularization in Overparametrized Models via Noise Injection](https://mlsanity.com/paper/2206.04613/) (2022)
- [Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications](https://mlsanity.com/paper/1905.00563/) (2019)
- [Convolutional Complex Knowledge Graph Embeddings](https://mlsanity.com/paper/2008.03130/) (2020)
- [Multi-Label Adversarial Perturbations](https://mlsanity.com/paper/1901.00546/) (2019)
- [Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods](https://mlsanity.com/paper/2111.03120/) (2021)
- [Convolutional Hypercomplex Embeddings for Link Prediction](https://mlsanity.com/paper/2106.15230/) (2021)
- [Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence](https://mlsanity.com/paper/1705.03202/) (2017)
- [Poisoning Knowledge Graph Embeddings via Relation Inference Patterns](https://mlsanity.com/paper/2111.06345/) (2021)
- [Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning](https://mlsanity.com/paper/2111.06103/) (2021)
- [Hardware-agnostic Computation for Large-scale Knowledge Graph Embeddings](https://mlsanity.com/paper/2207.08544/) (2022)

## Abstract (arXiv)

Knowledge Graph Embedding (KGE) transforms a discrete Knowledge Graph (KG) into a continuous vector space facilitating its use in various AI-driven applications like Semantic Search, Question Answering, or Recommenders. While KGE approaches are effective in these applications, most existing approaches assume that all information in the given KG is correct. This enables attackers to influence the output of these approaches, e.g., by perturbing the input. Consequently, the robustness of such KGE approaches has to be addressed. Recent work focused on adversarial attacks. However, non-adversarial attacks on all attack surfaces of these approaches have not been thoroughly examined. We close this gap by evaluating the impact of non-adversarial attacks on the performance of 5 state-of-the-art KGE algorithms on 5 datasets with respect to attacks on 3 attack surfaces-graph, parameter, and label perturbation. Our evaluation results suggest that label perturbation has a strong effect on the KGE performance, followed by parameter perturbation with a moderate and graph with a low effect.