Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation

About

Graph foundation models aim to learn transferable knowledge from diverse graphs for generalization to unseen graphs and tasks. Unlike text and images, graphs lack a shared vocabulary or regular spatial grid, making cross-graph transfer challenging. This challenge comes from both feature discrepancies and, more critically, diverse graph structures. Existing GFMs mainly improve transferability by unifying feature spaces or incorporating structural tokens and vocabularies. However, existing topology-aware designs still have limitations. Structural tokens are usually discrete, while structural vocabularies often rely on predefined substructures such as trees and cycles, whose limited coverage may miss richer relational patterns across graphs. Moreover, graph signals contain both high-frequency local patterns and smoother low-frequency patterns, which require different propagation behaviors. These components are often entangled in raw graph signals, while this spectral perspective is rarely explored in existing GFMs. To address these challenges, we propose SPG, a graph foundation model with spectral parsing and prototype-guided spatial propagation. SPG applies learnable Chebyshev filters to decompose node features into multiple spectral responses, reducing the mismatch between frequency-specific graph signals and propagation behaviors. It then constructs a Gromov-Wasserstein prototype geometry to distill transferable pairwise relations beyond predefined substructures into a shared structural space. The learned prototype geometry is further projected back as a prototype-guided propagation operator. Experiments demonstrate consistent improvements in cross-domain generalization.

Ankang Yang, Jitao Zhao, Dongxiao He, Liang Yang, Di Jin, Weixiong Zhang• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationProducts
Accuracy81.89
94
Graph ClassificationENZYMES (10-fold cross-validation)
Accuracy49.29
94
Node ClassificationCora In-domain
Accuracy84.1
18
Node ClassificationPhoto In-domain
Accuracy93.6
18
Node ClassificationCS In-domain
Accuracy93.45
18
Node ClassificationPhysics Cross-domain
Accuracy95.83
18
Node ClassificationCiteseer Cross-domain
Accuracy72.81
18
Node ClassificationPubmed Cross-domain
Accuracy87.41
18
Node ClassificationCornell Cross-domain
Accuracy61.24
18
Node ClassificationWisconsin Cross-domain
Accuracy68.75
18
Showing 10 of 19 rows

Other info

Follow for update