Adversarial Explanations for Knowledge Graph Embeddings

Carmona, Chris U.; Aubet, François-Xavier; Flunkert, Valentín; Gasthaus, Jan

doi:10.24963/ijcai.2022/391

Cited by 11 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Description: An adversarial attack against knowledge graph embedding aims at identifying the training instances that are most influential to the model's predictions on test instances. Existing works in this area are limited (Bhardwaj et al 2021;Betz, Meilicke, and Stuckenschmidt 2022), and even more limited is the design of a defense mechanism to alleviate the effect of adversarial attacks against knowledge graph embedding methods.…”

Section: Cross Domain Clusteringmentioning

confidence: 99%

Learning Better Representations Using Auxiliary Knowledge

Rezayi¹

2023

AAAI

View full text Add to dashboard Cite

Representation Learning is the core of Machine Learning and Artificial Intelligence as it summarizes input data points into low dimensional vectors. This low dimensional vectors should be accurate portrayals of the input data, thus it is crucial to find the most effective and robust representation possible for given input as the performance of the ML task is dependent on the resulting representations. In this summary, we discuss an approach to augment representation learning which relies on external knowledge. We briefly describe the shortcoming of the existing techniques and describe how an auxiliary knowledge source could result in obtaining improved representations.

show abstract

Section: Cross Domain Clusteringmentioning

confidence: 99%

Learning Better Representations Using Auxiliary Knowledge

Rezayi¹

2023

AAAI

View full text Add to dashboard Cite

show abstract

“…Rule ( 4) is a U c rule which states that a person is female, if she is married to a person that is male. A typical example for a U d rule is Rule (5), which says that an actor is someone who acts (in a film).…”

Section: Language Biasmentioning

confidence: 99%

“…The increased focus on sub-symbolic representations in the past decade, which was mainly driven by the flexibility and predictive quality achievable with end-to-end learning, somewhat conversely motivated the revival of the usage of symbolic methods due to an urgent need for explainability. Along these lines, it has been shown that AnyBURL can be utilized to explain predictions made by a latent model when restricting the types of learned rules [5]. Moreover, a symbolic model, when performing competitively in regard to predictive quality, represents a standalone alternative to a latent model as it is inherently explainable.…”

mentioning

confidence: 99%

Anytime bottom-up rule learning for large-scale knowledge graph completion

Meilicke,

Chekol,

Betz

et al. 2023

The VLDB Journal

Self Cite

View full text Add to dashboard Cite

Knowledge graph completion is the task of predicting correct facts that can be expressed by the vocabulary of a given knowledge graph, which are not explicitly stated in that graph. Broadly, there are two main approaches for solving the knowledge graph completion problem. Sub-symbolic approaches embed the nodes and/or edges of a given graph into a low-dimensional vector space and use a scoring function to determine the plausibility of a given fact. Symbolic approaches learn a model that remains within the primary representation of the given knowledge graph. Rule-based approaches are well-known examples. One such approach is AnyBURL. It works by sampling random paths, which are generalized into Horn rules. Previously published results show that the prediction quality of AnyBURL is close to current state of the art with the additional benefit of offering an explanation for a predicted fact. In this paper, we propose several improvements and extensions of AnyBURL. In particular, we focus on AnyBURL’s capability to be successfully applied to large and very large datasets. Overall, we propose four separate extensions: (i) We add to each rule a set of pairwise inequality constraints which enforces that different variables cannot be grounded by the same entities, which results into more appropriate confidence estimations. (ii) We introduce reinforcement learning to guide path sampling in order to use available computational resources more efficiently. (iii) We propose an efficient sampling strategy to approximate the confidence of a rule instead of computing its exact value. (iv) We develop a new multithreaded AnyBURL, which incorporates all previously mentioned modifications. In an experimental study, we show that our approach outperforms both symbolic and sub-symbolic approaches in large-scale knowledge graph completion. It has a higher prediction quality and requires significantly less time and computational resources.

show abstract

“…AnyBURL (Meilicke et al, 2019) is the successor of RuleN (Meilicke et al, 2018). It is shown to be competitive to neural approaches (Rossi et al, 2021;Meilicke et al, 2023) and it can be utilized to explain predictions made by embedding models (Betz et al, 2022a). Other approaches are tailored towards large graphs (Fan et al, 2022;Chen et al, 2016) or to learn negative rules (Ortona et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

“…Rule application refers to predicting previously unseen facts given a set of rules and the input or training KG. We can describe it compactly with the recently introduced concept of one-step-entailment (Betz et al, 2022a). Let C be a set of rules and G a KG.…”

Section: Rules and Applicationmentioning

confidence: 99%

Supervised Knowledge Aggregation for Knowledge Graph Completion

Betz

Meilicke

Stuckenschmidt

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Rule learning approaches for knowledge graph completion are efficient, interpretable and competitive to purely neural models. The rule aggregation problem is concerned with finding one plausibility score for a candidate fact which was simultaneously predicted by multiple rules. Although the problem is ubiquitous, as data-driven rule learning can result in noisy and large rule sets, it is underrepresented in the literature and its theoretical foundations have not been studied before in this context. In this work, we demonstrate that existing aggregation approaches can be expressed as marginal inference operations over the predicting rules. In particular, we show that the common Max-aggregation strategy, which scores candidates based on the rule with the highest confidence, has a probabilistic interpretation. Finally, we propose an efficient and overlooked baseline which combines the previous strategies and is competitive to computationally more expensive approaches.

show abstract

Adversarial Explanations for Knowledge Graph Embeddings

Cited by 11 publications

References 22 publications

Learning Better Representations Using Auxiliary Knowledge

Learning Better Representations Using Auxiliary Knowledge

Anytime bottom-up rule learning for large-scale knowledge graph completion

Supervised Knowledge Aggregation for Knowledge Graph Completion

Contact Info

Product

Resources

About