ASWT-SGNN: Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network
This work addresses a domain-specific problem in graph machine learning by improving efficiency and flexibility for node representation learning, though it is incremental as it builds on existing graph comparative learning methods.
The paper tackles the inflexibility and high computational cost of graph convolutional neural networks in self-supervised learning by proposing ASWT-SGNN, which uses adaptive spectral wavelet transforms to enable flexible neighborhood aggregation and reduces complexity, achieving comparable performance to state-of-the-art models in node classification tasks on eight benchmark datasets.
Graph Comparative Learning (GCL) is a self-supervised method that combines the advantages of Graph Convolutional Networks (GCNs) and comparative learning, making it promising for learning node representations. However, the GCN encoders used in these methods rely on the Fourier transform to learn fixed graph representations, which is inherently limited by the uncertainty principle involving spatial and spectral localization trade-offs. To overcome the inflexibility of existing methods and the computationally expensive eigen-decomposition and dense matrix multiplication, this paper proposes an Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network (ASWT-SGNN). The proposed method employs spectral adaptive polynomials to approximate the filter function and optimize the wavelet using contrast loss. This design enables the creation of local filters in both spectral and spatial domains, allowing flexible aggregation of neighborhood information at various scales and facilitating controlled transformation between local and global information. Compared to existing methods, the proposed approach reduces computational complexity and addresses the limitation of graph convolutional neural networks, which are constrained by graph size and lack flexible control over the neighborhood aspect. Extensive experiments on eight benchmark datasets demonstrate that ASWT-SGNN accurately approximates the filter function in high-density spectral regions, avoiding costly eigen-decomposition. Furthermore, ASWT-SGNN achieves comparable performance to state-of-the-art models in node classification tasks.