Providing Post-Hoc Explanation for Node Representation Learning Models Through Inductive Conformal Predictions
Learning with graph-structured data, such as social, biological, and financial networks, requires effective low-dimensional representations to handle their large and complex interactions. Recently, with the advances of neural networks and embedding algorithms, many unsupervised approaches have been...
Main Author: | Hogun Park |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10003193/ |
Similar Items
-
An Empirical Comparison of Interpretable Models to Post-Hoc Explanations
by: Parisa Mahya, et al.
Published: (2023-05-01) -
Explanations for Neural Networks by Neural Networks
by: Sascha Marton, et al.
Published: (2022-01-01) -
Surrogate explanations for role discovery on graphs
by: Eoghan Cunningham, et al.
Published: (2023-05-01) -
Benchmarking the influence of pre-training on explanation performance in MR image classification
by: Marta Oliveira, et al.
Published: (2024-02-01) -
Specific-Input LIME Explanations for Tabular Data Based on Deep Learning Models
by: Junkang An, et al.
Published: (2023-07-01)