[PDF][PDF] Semantic web technologies for explainable machine learning models: A literature review.
Due to their tremendous potential in predictive tasks, Machine Learning techniques such as
Artificial Neural Networks have received great attention from both research and practice …
Artificial Neural Networks have received great attention from both research and practice …
Attention-based explainable friend link prediction with heterogeneous context information
J Zheng, Z Qin, S Wang, D Li - Information Sciences, 2022 - Elsevier
Friend link prediction is an important research problem in recommender systems. Existing
network embedding and knowledge embedding methods mainly consider the structural …
network embedding and knowledge embedding methods mainly consider the structural …
Advances in data management in the big data era
Highly-heterogeneous and fast-arriving large amounts of data, otherwise said Big Data,
induced the development of novel Data Management technologies. In this paper, the …
induced the development of novel Data Management technologies. In this paper, the …
Efficiently counting complex multilayer temporal motifs in large-scale networks
This paper proposes novel algorithms for efficiently counting complex network motifs in
dynamic networks that are changing over time. Network motifs are small characteristic …
dynamic networks that are changing over time. Network motifs are small characteristic …
[PDF][PDF] Towards Socio-Technical Design of Explicative Systems: Transparent, Interpretable and Explainable Analytics and Its Perspectives in Social Interaction …
M Atzmueller - AfCAI, 2019 - ceur-ws.org
This paper outlines an approach towards socio-technical design of explicative systems
enabling transparent, interpretable and explainable analytics. We sketch the TIE approach …
enabling transparent, interpretable and explainable analytics. We sketch the TIE approach …
Explanations for network embedding-based link predictions
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 …
work with, as many machine learning methods may not be applied to them directly. Network …
Regularized online tensor factorization for sparse knowledge graph embeddings
Abstract Knowledge Graphs represent real-world facts and are used in several applications;
however, they are often incomplete and have many missing facts. Link prediction is the task …
however, they are often incomplete and have many missing facts. Link prediction is the task …
Evaluating Link Prediction Explanations for Graph Neural Networks
Abstract Graph Machine Learning (GML) has numerous applications, such as node/graph
classification and link prediction, in real-world domains. Providing human-understandable …
classification and link prediction, in real-world domains. Providing human-understandable …
Agent-based vector-label propagation for explaining social network structures
Abstract Even though Social Network Analysis is quite helpful in studying the structural
properties of interconnected systems, real-world networks reveal much more hidden …
properties of interconnected systems, real-world networks reveal much more hidden …
Influence functions for interpretable link prediction in knowledge graphs for intelligent environments
Knowledge graphs are large, graph-structured databases used in many use-case scenarios
such as Intelligent Environments. Many Artificial Intelligent latent feature models are used to …
such as Intelligent Environments. Many Artificial Intelligent latent feature models are used to …