AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks
In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and heterogeneous graphs-simultaneously. This challenge has led to the manual design of GNNs tailored to specific graph types, but these approaches are limited by the high cost of labor and the constraints of expert knowledge, which cannot keep up with the rapid growth of graph data. To overcome these challenges, we propose AutoSGNN, an automated framework for discovering propagation mechanisms in spectral GNNs. AutoSGNN unifies the search space for spectral GNNs by integrating large language models with evolutionary strategies to automatically generate architectures that adapt to various graph types. Extensive experiments on nine widely-used datasets, encompassing both homophilic and heterophilic graphs, demonstrate that AutoSGNN outperforms state-of-the-art spectral GNNs and graph neural architecture search methods in both performance and efficiency.
Code (1)
Tasks
Neural Architecture SearchSimilar Papers 제목 키워드 기반
Node Embedding via Word Embedding for Network Community Discovery
Neural node embeddings have recently emerged as a powerful representation for supervised learning tasks involving graph-structured data. We leverage this recent advance to develop a novel algorithm for unsupervised commu…
ClusteringGraph GenerationGeometry-Induced Diffusion on Graphs: A Learnable Weighted Laplacian for Spectral GNNs
Long-range graph tasks are challenging for Graph Neural Networks (GNNs): global mechanisms such as attention or rewiring schemes can be computationally expensive, while deep local propagation is prone to vanishing gradie…
Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization
In this paper, we propose REASON, a novel framework that enables the automatic discovery of both intra-level (i.e., within-network) and inter-level (i.e., across-network) causal relationships for root cause localization.…
Causal DiscoveryTime SeriesTime Series AnalysisSpectral Analysis of Fake News Propagation
How can we systematically represent the propagation of information? The propagation structure of fake news has been shown to be an important cue for detecting it; yet, existing propagation-based fake news detection metho…
Fake News DetectionLaplacian-LoRA: Delaying Oversmoothing in Deep GCNs via Spectral Low-Rank Adaptation
Oversmoothing is a fundamental limitation of deep graph convolutional networks (GCNs), causing node representations to collapse as depth increases. While many prior approaches mitigate this effect through architectural m…