← Search

Mohammad Mahdi Omati

1 accepted papers

2026

Exact Combinatorial Multi-Class Graph Cuts for Semi-Supervised Learning

AAAI 2026technical

Semi-supervised learning (SSL) on graphs is critical in applications where labeled data are scarce and costly, yet existing graph-based methods often degrade under extreme label sparsity or class imbalance, yielding trivial or unstable solutions. We introduce \textbf{CombCut}, the first exact combin

Cited by 0SourcePDFScholar