Huan Liu has received an award from the National Science Foundation to explore how graph data is used in real-world application, including social media data. His research paper, titled “III: SMALL: Graph Contrastive Learning for Few-Shot Node Classification,” looks at large data sets and how they can be labor intensive and time consuming to annotate or label. There is a pressing need to address the labeled data scarcity problem for machine learning and data mining to effectively deal with big data, like graph data. When we can only label a minuscule amount of data, can we learn well from big graph data? Graph few-shot node classification, in which learning can occur when only a small amount of data are labeled, is one such problem for which researchers strive to find novel solutions.
Advancing few-shot node classification
