FUSE: Fast Semi-Supervised Node Embedding Learning via Structural and Label-Aware Optimization
This addresses the challenge of efficient node classification in real-world graphs with sparse features, offering a faster alternative to existing methods, though it appears incremental in its hybrid approach.
The paper tackles the problem of node classification in graphs with limited node features by introducing a fast semi-supervised embedding framework that jointly optimizes structural preservation, supervised regularization, and label propagation. It achieves classification accuracy comparable to or better than state-of-the-art methods with significantly reduced computational cost.
Graph-based learning is a cornerstone for analyzing structured data, with node classification as a central task. However, in many real-world graphs, nodes lack informative feature vectors, leaving only neighborhood connectivity and class labels as available signals. In such cases, effective classification hinges on learning node embeddings that capture structural roles and topological context. We introduce a fast semi-supervised embedding framework that jointly optimizes three complementary objectives: (i) unsupervised structure preservation via scalable modularity approximation, (ii) supervised regularization to minimize intra-class variance among labeled nodes, and (iii) semi-supervised propagation that refines unlabeled nodes through random-walk-based label spreading with attention-weighted similarity. These components are unified into a single iterative optimization scheme, yielding high-quality node embeddings. On standard benchmarks, our method consistently achieves classification accuracy at par with or superior to state-of-the-art approaches, while requiring significantly less computational cost.