TY - GEN
T1 - Node Classification with Bounded Error Rates
AU - Wijegunawardana, Pivithuru
AU - Gera, Ralucca
AU - Soundarajan, Sucheta
N1 - Publisher Copyright:
© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020.
PY - 2020
Y1 - 2020
N2 - Node classification algorithms are widely used for the task of node label prediction in partially labeled graph data. In many problems, a user may wish to associate a confidence level with a prediction such that the error in the prediction is guaranteed. We propose adopting the Conformal Prediction framework [17] to obtain guaranteed error bounds in node classification problem. We show how this framework can be applied to (1) obtain predictions with guaranteed error bounds, and (2) improve the accuracy of the prediction algorithms. Our experimental results show that the Conformal Prediction framework can provide up to a 30% improvement in node classification algorithm accuracy while maintaining guaranteed error bounds on predictions.
AB - Node classification algorithms are widely used for the task of node label prediction in partially labeled graph data. In many problems, a user may wish to associate a confidence level with a prediction such that the error in the prediction is guaranteed. We propose adopting the Conformal Prediction framework [17] to obtain guaranteed error bounds in node classification problem. We show how this framework can be applied to (1) obtain predictions with guaranteed error bounds, and (2) improve the accuracy of the prediction algorithms. Our experimental results show that the Conformal Prediction framework can provide up to a 30% improvement in node classification algorithm accuracy while maintaining guaranteed error bounds on predictions.
KW - Bounded error rates
KW - Conformal prediction
KW - Node classification
UR - http://www.scopus.com/inward/record.url?scp=85081267097&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081267097&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-40943-2_3
DO - 10.1007/978-3-030-40943-2_3
M3 - Conference contribution
AN - SCOPUS:85081267097
SN - 9783030409425
T3 - Springer Proceedings in Complexity
SP - 26
EP - 38
BT - Complex Networks XI - Proceedings of the 11th Conference on Complex Networks, CompleNet 2020
A2 - Barbosa, Hugo
A2 - Menezes, Ronaldo
A2 - Gomez-Gardenes, Jesus
A2 - Gonçalves, Bruno
A2 - Mangioni, Giuseppe
A2 - Oliveira, Marcos
PB - Springer
T2 - 11th International Conference on Complex Networks, CompleNet 2020
Y2 - 31 March 2020 through 3 April 2020
ER -