Skip to content

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Book Open access Nov 2026

Robust Node Classification via Noise-robust Views and Prototype Relabeling

How do we classify nodes accurately on heterophilic graphs when training labels are infected by neighbors' majority classes? In many real-world applications, annotators lack sufficient evidence for each node in isolation and thus rely on its neighborhood context, causing labels to drift toward the neighborhood majority...

Hoyoung Yoon, J. Kim, U. Kang · 0 citations
Book Open access Nov 2026

Sipu: Accurate Graph-based Positive-Unlabeled Learning under Heterophily

Sipu is proposed, an accurate graph-based PU learning method for heterophilic graphs that mitigates negative transfer from heterophilic neighbors while preserving higher-order homophilic information through positive paths.

Shihyun Park, J. Kim, U. Kang · 0 citations
#edge computing Book Open access Nov 2026

Sipu: Accurate Graph-based Positive-Unlabeled Learning under Heterophily

How can we accurately train a binary node classifier on heterophilic graphs when only positive and unlabeled nodes are available? This setting commonly arises in real-world applications such as fraud detection, where only detected fraudsters are labeled as positive, while the remaining users are unlabeled and may inclu...

Shihyun Park, J. Kim, U. Kang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.