Semi-supervised Embedding in Attributed Networks with Outliers
This work addresses the challenge of robust representation learning in noisy attributed networks, with applications in web, text, image, and remote sensing domains, though it appears incremental as it builds on existing semi-supervised and outlier handling techniques.
The authors tackled the problem of learning low-dimensional vector representations in partially labeled attributed networks with outliers, proposing SEANO, which outperformed state-of-the-art methods in semi-supervised classification and outlier detection across various datasets, including a real-world flood mapping application.
In this paper, we propose a novel framework, called Semi-supervised Embedding in Attributed Networks with Outliers (SEANO), to learn a low-dimensional vector representation that systematically captures the topological proximity, attribute affinity and label similarity of vertices in a partially labeled attributed network (PLAN). Our method is designed to work in both transductive and inductive settings while explicitly alleviating noise effects from outliers. Experimental results on various datasets drawn from the web, text and image domains demonstrate the advantages of SEANO over state-of-the-art methods in semi-supervised classification under transductive as well as inductive settings. We also show that a subset of parameters in SEANO is interpretable as outlier score and can significantly outperform baseline methods when applied for detecting network outliers. Finally, we present the use of SEANO in a challenging real-world setting -- flood mapping of satellite images and show that it is able to outperform modern remote sensing algorithms for this task.