Explaining Link Prediction Systems based on Knowledge Graph Embeddings
Andrea Rossi,Donatella Firmani,Paolo Merialdo,Tommaso Teofili +3 more
- 10 Jun 2022
TL;DR: This paper proposes the novel Kelpie explainability framework, which can be applied to any embedding-based LP models independently from their architecture, and it explains predictions by identifying the combinations of training facts that have enabled them.
read more
Abstract: Link Prediction (LP) aims at tackling Knowledge Graph incompleteness by inferring new, missing facts from the already known ones. The rise of novel Machine Learning techniques has led researchers to develop LP models that represent Knowledge Graph elements as vectors in an embedding space. These models can outperform traditional approaches and they can be employed in multiple downstream tasks; nonetheless, they tend to be opaque, and are mostly regarded as black boxes. Their lack of interpretability limits our understanding of their inner mechanisms, and undermines the trust that users can place in them. In this paper, we propose the novel Kelpie explainability framework. Kelpie can be applied to any embedding-based LP models independently from their architecture, and it explains predictions by identifying the combinations of training facts that have enabled them. Kelpie can extract two complementary types of explanations, that we dub necessary and sufficient. We describe in detail both the structure and the implementation details of Kelpie, and thoroughly analyze its performance through extensive experiments. Our results show that Kelpie significantly outperforms baselines across almost all scenarios.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Sem@K: Is my knowledge graph embedding model semantic-aware?
TL;DR: In this article , the authors extend the Sem@$K$ metric to measure the capability of KGEM models to predict valid entities w.r.t. domain and range constrains.
6
Sem@K: Is my knowledge graph embedding model semantic-aware?
Nicolas Hubert,Pierre Monnin,Armelle Brun,Davy Monticolo +3 more
TL;DR: Sem@K is a metric that measures the capability of KGEMs to predict valid entities w.r.t. domain and range constraints. It provides a new perspective on KGEM quality and offers different conclusions on the predictive power of models than rank-based metrics.
5
Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation
Shuang Wang,B. Eravcı,Rustam Guliyev,Hakan Ferhatosmanoglu +3 more
TL;DR: The proposed GNN quantizer learns quantization ranges and reduces the model size with comparable accuracy even under low-bit quantization, and demonstrates superior performance in INT2 configurations across all stages of GNN, achieving a notable level of accuracy.
Path-based Explanation for Knowledge Graph Completion
Heng Chang,J. Ye,Alejo Lopez-Avila,Jinhua Du,Jia Li +4 more
- 24 Aug 2024
TL;DR: This study proposes Power-Link, a path-based Knowledge Graph Completion (KGC) explainer, leveraging a novel graph-powering technique for generating interpretable explanations, outperforming state-of-the-art baselines in interpretability, efficiency, and scalability.
Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching
Tianle Zhang,Yuchen Zhang,Kun Wang,Kai Wang,Beining Yang,Kaipeng Zhang,Wenqi Shao,Ping Liu,Joey Tianyi Zhou,Yang You +9 more
TL;DR: A novel graph condensation method named CTRL, which offers an optimized starting point closer to the original dataset's feature distribution and a more refined strategy for gradient matching and can effectively neutralize the impact of accumulated errors on the performance of condensed graphs.
4
References
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro,Sameer Singh,Carlos Guestrin +2 more
- 13 Aug 2016
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
WordNet: a lexical database for English
TL;DR: WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control.
16.9K
A Value for n-person Games
Lloyd S. Shapley
- 18 Mar 1952
TL;DR: In this paper, an examination of elementary properties of a value for the essential case is presented, which is deduced from a set of three axioms, having simple intuitive interpretations.
•Proceedings Article
Translating Embeddings for Modeling Multi-relational Data
Antoine Bordes,Nicolas Usunier,Alberto Garcia-Duran,Jason Weston,Oksana Yakhnenko +4 more
- 05 Dec 2013
TL;DR: TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.