GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learning

TL;DR

GraphVec introduces a domain-agnostic graph embedding method that leverages spectral features and a novel alignment algorithm to improve cross-domain graph classification and clustering.

Contribution

The paper presents GraphVec, a new spectral-based graph vectorization model with a density-maximization alignment algorithm, enhancing transferability across heterogeneous graph datasets.

Findings

Outperforms 15 comparison methods on 13 datasets in cross-domain tasks.

Achieves state-of-the-art results in few-shot graph classification and clustering.

Provides strong node-level representations competitive with graph prompt methods.

Abstract

Learning universal graph representations across heterogeneous domains is difficult because graph datasets differ in topology, node-attribute semantics, feature dimensions, and even attribute availability. We propose GraphVec, a language-model-free graph vectorization model that maps diverse graphs into transferable fixed-dimensional embeddings for graph-level tasks. Instead of directly using incomparable raw node attributes, GraphVec constructs multi-scale global graphs over all nodes in each dataset and extracts spectral embeddings to obtain domain-agnostic relational features. To make these spectral features comparable across datasets, we introduce a density-maximization mean alignment algorithm over orthogonal transformations and prove its monotonic convergence. GraphVec further combines a GIN--Graph Transformer backbone with a multi-layer reference distribution module, which preserves node-level distributional information beyond standard pooling. We also provide a generalization error bound for the proposed model. Experiments on 13 datasets with more than 15 comparison methods demonstrate that GraphVec consistently outperforms strong graph pretraining baselines in cross-domain few-shot graph classification and graph clustering. Beyond graph-level tasks, GraphVec also yields strong node-level representations, achieving competitive performance on few-shot node classification against representative graph prompt learning methods.