Automated Evaluation of GNN Explanations with Neuro Symbolic Reasoning

Vanya Bannihatti Kumar, Balaji Ganesan, Muhammed Ameen, Devbrat Sharma, Arvind Agarwal
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, PMLR 176:314-318, 2022.

Abstract

Explaining Graph Neural Networks predictions to end users of AI applications in easily understandable terms remains an unsolved problem. In particular, we do not have well developed methods for automatically evaluating explanations, in ways that are closer to how users consume those explanations. Based on recent application trends and our own experiences in real world problems, we propose an automatic evaluation approach for GNN Explanations using Neuro Symbolic Reasoning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v176-kumar22a, title = {Automated Evaluation of GNN Explanations with Neuro Symbolic Reasoning}, author = {Kumar, Vanya Bannihatti and Ganesan, Balaji and Ameen, Muhammed and Sharma, Devbrat and Agarwal, Arvind}, booktitle = {Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track}, pages = {314--318}, year = {2022}, editor = {Kiela, Douwe and Ciccone, Marco and Caputo, Barbara}, volume = {176}, series = {Proceedings of Machine Learning Research}, month = {06--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v176/kumar22a/kumar22a.pdf}, url = {https://proceedings.mlr.press/v176/kumar22a.html}, abstract = {Explaining Graph Neural Networks predictions to end users of AI applications in easily understandable terms remains an unsolved problem. In particular, we do not have well developed methods for automatically evaluating explanations, in ways that are closer to how users consume those explanations. Based on recent application trends and our own experiences in real world problems, we propose an automatic evaluation approach for GNN Explanations using Neuro Symbolic Reasoning.} }
Endnote
%0 Conference Paper %T Automated Evaluation of GNN Explanations with Neuro Symbolic Reasoning %A Vanya Bannihatti Kumar %A Balaji Ganesan %A Muhammed Ameen %A Devbrat Sharma %A Arvind Agarwal %B Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track %C Proceedings of Machine Learning Research %D 2022 %E Douwe Kiela %E Marco Ciccone %E Barbara Caputo %F pmlr-v176-kumar22a %I PMLR %P 314--318 %U https://proceedings.mlr.press/v176/kumar22a.html %V 176 %X Explaining Graph Neural Networks predictions to end users of AI applications in easily understandable terms remains an unsolved problem. In particular, we do not have well developed methods for automatically evaluating explanations, in ways that are closer to how users consume those explanations. Based on recent application trends and our own experiences in real world problems, we propose an automatic evaluation approach for GNN Explanations using Neuro Symbolic Reasoning.
APA
Kumar, V.B., Ganesan, B., Ameen, M., Sharma, D. & Agarwal, A.. (2022). Automated Evaluation of GNN Explanations with Neuro Symbolic Reasoning. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, in Proceedings of Machine Learning Research 176:314-318 Available from https://proceedings.mlr.press/v176/kumar22a.html.

Related Material