# Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications

arXiv: https://arxiv.org/abs/1905.00563 · HTML: https://mlsanity.com/paper/1905.00563/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2019.

## Built on by (most cited first, 25 of 25)

- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [An Empirical Comparison of Instance Attribution Methods for NLP](https://mlsanity.com/paper/2104.04128/) (2021)
- [Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods](https://mlsanity.com/paper/2111.03120/) (2021)
- [Poisoning Knowledge Graph Embeddings via Relation Inference Patterns](https://mlsanity.com/paper/2111.06345/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [On the Security Risks of Knowledge Graph Reasoning](https://mlsanity.com/paper/2305.02383/) (2023)
- [Explaining the Road Not Taken](https://mlsanity.com/paper/2103.14973/) (2021)
- [Interpretability in Activation Space Analysis of Transformers: A Focused Survey](https://mlsanity.com/paper/2302.09304/) (2023)
- [KGExplainer: Towards Exploring Connected Subgraph Explanations for Knowledge Graph Completion](https://mlsanity.com/paper/2404.03893/) (2024)
- [Untargeted Adversarial Attack on Knowledge Graph Embeddings](https://mlsanity.com/paper/2405.10970/) (2024)
- [Towards Explaining Subjective Ground of Individuals on Social Media](https://mlsanity.com/paper/2211.09953/) (2022)
- [Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examples](https://mlsanity.com/paper/2212.02651/) (2022)
- [eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules](https://mlsanity.com/paper/2412.04846/) (2024)
- [NODDLE: Node2vec based deep learning model for link prediction](https://mlsanity.com/paper/2305.16421/) (2023)
- [Resilience in Knowledge Graph Embeddings](https://mlsanity.com/paper/2410.21163/) (2024)
- [Unifying Post-hoc Explanations of Knowledge Graph Completions](https://mlsanity.com/paper/2507.22951/) (2025)
- [Adversarial Robustness of Representation Learning for Knowledge Graphs](https://mlsanity.com/paper/2210.00122/) (2022)
- [Veni, Vidi, Vici: Solving the Myriad of Challenges before Knowledge Graph Learning](https://mlsanity.com/paper/2402.06098/) (2024)
- [From Latent to Lucid: Transforming Knowledge Graph Embeddings into Interpretable Structures with KGEPrisma](https://mlsanity.com/paper/2406.01759/) (2024)
- [Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attacks](https://mlsanity.com/paper/2407.06855/) (2024)
- [Explaining Graph Neural Networks for Node Similarity on Graphs](https://mlsanity.com/paper/2407.07639/) (2024)
- [GRainsaCK: a Comprehensive Software Library for Benchmarking Explanations of Link Prediction Tasks on Knowledge Graphs](https://mlsanity.com/paper/2508.08815/) (2025)
- [LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings](https://mlsanity.com/paper/2510.11584/) (2025)
- [CQD-SHAP: Explainable Complex Query Answering via Shapley Values](https://mlsanity.com/paper/2510.15623/) (2025)
- [From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphs](https://mlsanity.com/paper/2609.11170/) (2026)

## Abstract (arXiv)

Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on improving accuracy and overlook other aspects such as robustness and interpretability. In this paper, we propose adversarial modifications for link prediction models: identifying the fact to add into or remove from the knowledge graph that changes the prediction for a target fact after the model is retrained. Using these single modifications of the graph, we identify the most influential fact for a predicted link and evaluate the sensitivity of the model to the addition of fake facts. We introduce an efficient approach to estimate the effect of such modifications by approximating the change in the embeddings when the knowledge graph changes. To avoid the combinatorial search over all possible facts, we train a network to decode embeddings to their corresponding graph components, allowing the use of gradient-based optimization to identify the adversarial modification. We use these techniques to evaluate the robustness of link prediction models (by measuring sensitivity to additional facts), study interpretability through the facts most responsible for predictions (by identifying the most influential neighbors), and detect incorrect facts in the knowledge base.