Explainable and Efficient Link Prediction in Real-World Network Data

Engelen, Jesper E. van; Boekhout, Hanjo D.; Takes, Frank W.

doi:10.1007/978-3-319-46349-0_26

Cited by 10 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xie et al (2017) proposed an embedding model and designed a learning algorithm to induce interpretable sparse representations in it. Engelen et al (2016) developed an efficient and explainable technique for link prediction using topological features.…”

Section: Interpreting Embedding Models: Related Workmentioning

confidence: 99%

Interpreting embedding models of knowledge bases.

Gusmão¹

View full text Add to dashboard Cite

Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. In this paper, we adapt "pedagogical approaches" (from the literature on neural networks) so as to interpret embedding models by extracting weighted Horn rules from them. We show how pedagogical approaches have to be adapted to take upon the large-scale relational aspects of knowledge bases and show experimentally their strengths and weaknesses.

show abstract

Section: Interpreting Embedding Models: Related Workmentioning

confidence: 99%

Interpreting embedding models of knowledge bases.

Gusmão¹

View full text Add to dashboard Cite

show abstract

“…Note that the exact method also has substantial memory cost: 10.4 Gb for MovieLens and on DBLP it went out of memory. On MovieLens, the time was computed only for one k, and multiplied by n − 2 to get an estimated total time for all k.There are a few existing works that aim to explain link predictions (see, e.g [7,2,27]…”

mentioning

confidence: 99%

Explanations for Network Embedding-Based Link Predictions

Kang

Lijffijt

Bie

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Graphs (also called networks) are powerful data abstractions, but they are challenging to work with, as many machine learning methods may not be applied to them directly. Network Embedding (NE) methods resolve this by learning vector representations for the nodes, for subsequent use in downstream machinelearning tasks. Link Prediction is one such important downstream task, used for example in recommender systems. NE methods perform exceedingly well in accuracy for Link Prediction, but predictions following from the embeddings, whose dimensions have no intrinsic meaning, are not straightforward to understand. Explaining why predictions are made can increase trustworthiness, help understand the underlying models and give insight into what features of the network are important in light of the predictions, and answer posed regulatory requirements on the ability to explain machine-learning-based decisions. We study the problem of providing explanations for NE-based link predictions and introduce ExplaiNE, an approach to derive counterfactual explanations by identifying links in the network that explain link predictions. We show how ExplaiNE can be used generically on NE-based methods and consider ExplaiNE in more detail for Conditional Network Embedding, a particularly suitable state-of-art NE method. Extensive experiments demonstrate ExplaiNE's accuracy and scalability.

show abstract