Confidence-based Graph Convolutional Networks for Semi-Supervised Learning

Shikhar Vashishth, Prateek Yadav, Manik Bhandari, Partha Talukdar
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:1792-1801, 2019.

Abstract

Predicting properties of nodes in a graph is an important problem with applications in a variety of domains. Graph-based Semi Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds, and then utilizing the graph structure to predict label scores for the rest of the nodes in the graph. Recently, Graph Convolutional Networks (GCNs) have achieved impressive performance on the graph-based SSL task. In addition to label scores, it is also desirable to have confidence scores associated with them. Unfortunately, confidence estimation in the context of GCN has not been previously explored. We fill this important gap in this paper and propose ConfGCN, which estimates labels scores along with their confidences jointly in GCN-based setting. ConfGCN uses these estimated confidences to determine the influence of one node on another during neighborhood aggregation, thereby acquiring anisotropic capabilities. Through extensive analysis and experiments on standard benchmarks, we find that ConfGCN is able to outperform state-of-the-art baselines. We have made ConfGCN’s source code available to encourage reproducible research.

Cite this Paper

BibTeX
@InProceedings{pmlr-v89-vashishth19a, title = {Confidence-based Graph Convolutional Networks for Semi-Supervised Learning}, author = {Vashishth, Shikhar and Yadav, Prateek and Bhandari, Manik and Talukdar, Partha}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {1792--1801}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/vashishth19a/vashishth19a.pdf}, url = {https://proceedings.mlr.press/v89/vashishth19a.html}, abstract = {Predicting properties of nodes in a graph is an important problem with applications in a variety of domains. Graph-based Semi Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds, and then utilizing the graph structure to predict label scores for the rest of the nodes in the graph. Recently, Graph Convolutional Networks (GCNs) have achieved impressive performance on the graph-based SSL task. In addition to label scores, it is also desirable to have confidence scores associated with them. Unfortunately, confidence estimation in the context of GCN has not been previously explored. We fill this important gap in this paper and propose ConfGCN, which estimates labels scores along with their confidences jointly in GCN-based setting. ConfGCN uses these estimated confidences to determine the influence of one node on another during neighborhood aggregation, thereby acquiring anisotropic capabilities. Through extensive analysis and experiments on standard benchmarks, we find that ConfGCN is able to outperform state-of-the-art baselines. We have made ConfGCN’s source code available to encourage reproducible research.} }
Endnote
%0 Conference Paper %T Confidence-based Graph Convolutional Networks for Semi-Supervised Learning %A Shikhar Vashishth %A Prateek Yadav %A Manik Bhandari %A Partha Talukdar %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-vashishth19a %I PMLR %P 1792--1801 %U https://proceedings.mlr.press/v89/vashishth19a.html %V 89 %X Predicting properties of nodes in a graph is an important problem with applications in a variety of domains. Graph-based Semi Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds, and then utilizing the graph structure to predict label scores for the rest of the nodes in the graph. Recently, Graph Convolutional Networks (GCNs) have achieved impressive performance on the graph-based SSL task. In addition to label scores, it is also desirable to have confidence scores associated with them. Unfortunately, confidence estimation in the context of GCN has not been previously explored. We fill this important gap in this paper and propose ConfGCN, which estimates labels scores along with their confidences jointly in GCN-based setting. ConfGCN uses these estimated confidences to determine the influence of one node on another during neighborhood aggregation, thereby acquiring anisotropic capabilities. Through extensive analysis and experiments on standard benchmarks, we find that ConfGCN is able to outperform state-of-the-art baselines. We have made ConfGCN’s source code available to encourage reproducible research.
APA
Vashishth, S., Yadav, P., Bhandari, M. & Talukdar, P.. (2019). Confidence-based Graph Convolutional Networks for Semi-Supervised Learning. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:1792-1801 Available from https://proceedings.mlr.press/v89/vashishth19a.html.

Related Material