# Adversarial Sets for Regularising Neural Link Predictors

arXiv: https://arxiv.org/abs/1707.07596 · HTML: https://mlsanity.com/paper/1707.07596/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2017.

## Built on by (most cited first, 15 of 15)

- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey](https://mlsanity.com/paper/2108.11451/) (2021)
- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [How to Turn Your Knowledge Graph Embeddings into Generative Models](https://mlsanity.com/paper/2305.15944/) (2023)
- [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)
- [Semantic Strengthening of Neuro-Symbolic Learning](https://mlsanity.com/paper/2302.14207/) (2023)
- [Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study](https://mlsanity.com/paper/2107.13646/) (2021)
- [ER: Equivariance Regularizer for Knowledge Graph Completion](https://mlsanity.com/paper/2206.12142/) (2022)
- [Approximate Knowledge Graph Query Answering: From Ranking to Binary Classification](https://mlsanity.com/paper/2102.11389/) (2021)
- [Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction](https://mlsanity.com/paper/2103.11062/) (2021)
- [A Probabilistic Framework for Knowledge Graph Data Augmentation](https://mlsanity.com/paper/2110.13205/) (2021)
- [Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling](https://mlsanity.com/paper/2103.06198/) (2021)
- [Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge Graphs](https://mlsanity.com/paper/2106.14052/) (2021)
- [EM-NeSy: Expectation Maximization for Neurosymbolic Learning](https://mlsanity.com/paper/2606.14463/) (2026)

## Abstract (arXiv)

In adversarial training, a set of models learn together by pursuing competing goals, usually defined on single data instances. However, in relational learning and other non-i.i.d domains, goals can also be defined over sets of instances. For example, a link predictor for the is-a relation needs to be consistent with the transitivity property: if is-a(x_1, x_2) and is-a(x_2, x_3) hold, is-a(x_1, x_3) needs to hold as well. Here we use such assumptions for deriving an inconsistency loss, measuring the degree to which the model violates the assumptions on an adversarially-generated set of examples. The training objective is defined as a minimax problem, where an adversary finds the most offending adversarial examples by maximising the inconsistency loss, and the model is trained by jointly minimising a supervised loss and the inconsistency loss on the adversarial examples. This yields the first method that can use function-free Horn clauses (as in Datalog) to regularise any neural link predictor, with complexity independent of the domain size. We show that for several link prediction models, the optimisation problem faced by the adversary has efficient closed-form solutions. Experiments on link prediction benchmarks indicate that given suitable prior knowledge, our method can significantly improve neural link predictors on all relevant metrics.