Semi-supervised learning with max-margin graph cuts

TL;DR

This paper introduces a new semi-supervised learning algorithm that optimizes graph cuts for maximum margin, demonstrating superior performance over existing methods on various datasets.

Contribution

The paper presents a novel max-margin graph cut algorithm for semi-supervised learning, with theoretical error bounds and empirical validation showing improved results.

Findings

Outperforms manifold regularization SVMs on multiple datasets

Provides a theoretical bound on generalization error

Evaluates on synthetic and real-world datasets

Abstract

This paper proposes a novel algorithm for semisupervised learning. This algorithm learns graph cuts that maximize the margin with respect to the labels induced by the harmonic function solution. We motivate the approach, compare it to existing work, and prove a bound on its generalization error. The quality of our solutions is evaluated on a synthetic problem and three UCI ML repository datasets. In most cases, we outperform manifold regularization of support vector machines, which is a state-of-the-art approach to semi-supervised max-margin learning.