G-SPARC: SPectral ARchitectures tackling the Cold-start problem in Graph learning

Graphs play a central role in modeling complex relationships across various domains. Most graph learning methods rely heavily on neighborhood information, raising the question of how to handle cold-start nodes -- nodes with no known connections within the graph. These models often overlook the cold-start nodes, making them ineffective for real-world scenarios. To tackle this, we propose G-SPARC, a novel framework addressing cold-start nodes, that leverages generalizable spectral embedding. This framework enables extension to state-of-the-art methods making them suitable for practical applications. By utilizing a key idea of transitioning from graph representation to spectral representation, our approach is generalizable to cold-start nodes, capturing the global structure of the graph without relying on adjacency data. Experimental results demonstrate that our method outperforms existing models on cold-start nodes across various tasks like node classification, node clustering, and link prediction. G-SPARC provides a breakthrough built-in solution to the cold-start problem in graph learning. Our code will be publicly available upon acceptance. Graphs have advanced deep learning techniques across various domains, enabling tasks such as node classification, node clustering, and link prediction (Kipf & Welling, 2016a; Battaglia et al., 2018; LeCun et al., 1989; Yao et al., 2019; Chen et al., 2019).