Graph Embedding in the Graph Fractional Fourier Transform Domain
By: Changjie Sheng, Zhichao Zhang, Wei Yao
Potential Business Impact:
Improves computer understanding of complex data patterns.
Spectral graph embedding plays a critical role in graph representation learning by generating low-dimensional vector representations from graph spectral information. However, the embedding space of traditional spectral embedding methods often exhibit limited expressiveness, failing to exhaustively capture latent structural features across alternative transform domains. To address this issue, we use the graph fractional Fourier transform to extend the existing state-of-the-art generalized frequency filtering embedding (GEFFE) into fractional domains, giving birth to the generalized fractional filtering embedding (GEFRFE), which enhances embedding informativeness via the graph fractional domain. The GEFRFE leverages graph fractional domain filtering and a nonlinear composition of eigenvector components derived from a fractionalized graph Laplacian. To dynamically determine the fractional order, two parallel strategies are introduced: search-based optimization and a ResNet18-based adaptive learning. Extensive experiments on six benchmark datasets demonstrate that the GEFRFE captures richer structural features and significantly enhance classification performance. Notably, the proposed method retains computational complexity comparable to GEFFE approaches.
Similar Papers
Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspective
Machine Learning (CS)
Helps computers learn from different data types.
Spectrum Prediction in the Fractional Fourier Domain with Adaptive Filtering
Machine Learning (CS)
Predicts radio waves better for faster wireless.
Angular Graph Fractional Fourier Transform: Theory and Application
Machine Learning (Stat)
Improves computer understanding of complex data patterns.