Dine: Dimensional interpretability of node embeddings
Graph representation learning methods, such as node embeddings, are powerful
approaches to map nodes into a latent vector space, allowing their use for various graph …
approaches to map nodes into a latent vector space, allowing their use for various graph …
Self-explainable graph neural networks for link prediction
Graph Neural Networks (GNNs) have achieved state-of-the-art performance for link
prediction. However, GNNs suffer from poor interpretability, which limits their adoptions in …
prediction. However, GNNs suffer from poor interpretability, which limits their adoptions in …
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 …
Pytorch-geometric edge-a library for learning representations of graph edges
P Bielak, TJ Kajdanowicz - The First Learning on Graphs …, 2022 - openreview.net
Machine learning on graphs (GraphML) has been successfully deployed in a wide variety of
problem areas, as many real-world datasets are inherently relational. However, both …
problem areas, as many real-world datasets are inherently relational. However, both …
[图书][B] Toward Knowledge-Centric Natural Language Processing: Acquisition, Representation, Transfer, and Reasoning
Z Wang - 2022 - search.proquest.com
Past decades have witnessed the great success of modern Artificial Intelligence (AI) via
learning incredible statistical correlations from large-scale data. However, a knowledge gap …
learning incredible statistical correlations from large-scale data. However, a knowledge gap …