HopGAT: Hop-aware Supervision Graph Attention Networks for Sparsely Labeled Graphs
This addresses the problem of maintaining accuracy with limited labels in graph neural networks, particularly for domains like protein-protein interaction networks, though it appears incremental as it builds on existing graph attention methods.
The paper tackles node classification in sparsely labeled graphs by proposing HopGAT, which uses hop-aware attention supervision and simulated annealing learning. On a protein-protein interaction network with 40% labels, it achieves 94.6% accuracy, only 3.9% below the fully labeled performance of 98.5%.
Due to the cost of labeling nodes, classifying a node in a sparsely labeled graph while maintaining the prediction accuracy deserves attention. The key point is how the algorithm learns sufficient information from more neighbors with different hop distances. This study first proposes a hop-aware attention supervision mechanism for the node classification task. A simulated annealing learning strategy is then adopted to balance two learning tasks, node classification and the hop-aware attention coefficients, along the training timeline. Compared with state-of-the-art models, the experimental results proved the superior effectiveness of the proposed Hop-aware Supervision Graph Attention Networks (HopGAT) model. Especially, for the protein-protein interaction network, in a 40% labeled graph, the performance loss is only 3.9%, from 98.5% to 94.6%, compared to the fully labeled graph. Extensive experiments also demonstrate the effectiveness of supervised attention coefficient and learning strategies.