English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

There has been a recent surge of interest in designing Graph Neural Networks(GNNs) for semi-supervised learning tasks. Unfortunately this work has assumedthat the nodes labeled for use in training were selected uniformly at random(i.e. are an IID sample). However in many real world scenarios gathering labelsfor graph nodes is both expensive and inherently biased -- so this assumptioncan not be met. GNNs can suffer poor generalization when this occurs, byoverfitting to superfluous regularities present in the training data. In thiswork we present a method, Shift-Robust GNN (SR-GNN), designed to account fordistributional differences between biased training data and the graph's trueinference distribution. SR-GNN adapts GNN models for the presence ofdistributional shifts between the nodes which have had labels provided fortraining and the rest of the dataset. We illustrate the effectiveness of SR-GNNin a variety of experiments with biased training datasets on common GNNbenchmark datasets for semi-supervised learning, where we see that SR-GNNoutperforms other GNN baselines by accuracy, eliminating at least (~40%) of thenegative effects introduced by biased training data. On the largest dataset weconsider, ogb-arxiv, we observe an 2% absolute improvement over the baselineand reduce 30% of the negative effects.

Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data