SEAL trains a graph embedding network and a semisupervised discriminator adversarially so that the discriminator's divergence score selects which unlabeled nodes to label, improving node classification accuracy over prior active learning baselines.
Active Semi-Supervised Learning using Submodular Functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We consider active, semi-supervised learning in an offline transductive setting. We show that a previously proposed error bound for active learning on undirected weighted graphs can be generalized by replacing graph cut with an arbitrary symmetric submodular function. Arbitrary non-symmetric submodular functions can be used via symmetrization. Different choices of submodular functions give different versions of the error bound that are appropriate for different kinds of problems. Moreover, the bound is deterministic and holds for adversarially chosen labels. We show exactly minimizing this error bound is NP-complete. However, we also introduce for any submodular function an associated active semi-supervised learning method that approximately minimizes the corresponding error bound. We show that the error bound is tight in the sense that there is no other bound of the same form which is better. Our theoretical results are supported by experiments on real data.
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphs
SEAL trains a graph embedding network and a semisupervised discriminator adversarially so that the discriminator's divergence score selects which unlabeled nodes to label, improving node classification accuracy over prior active learning baselines.