ProGFM transfers graph knowledge across domains by learning a prototype bank of per-edge, per-dimension propagation strengths and using them to modulate message passing on unseen graphs.
Bridging Input Feature Spaces Towards Graph Foundation Models
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and dimensionality. This misalignment prevents graph models from generalizing across datasets, limiting their use as foundation models. In this work, we propose ALL-IN, a simple and theoretically grounded method that enables transferability across datasets with different input features. Our approach projects node features into a shared random space and constructs representations via covariance-based statistics, thus eliminating dependence on the original feature space. We show that the computed node-covariance operators and the resulting node representations are invariant in distribution to permutations of the input features. We further demonstrate that the expected operator exhibits invariance to general orthogonal transformations of the input features. Empirically, ALL-IN achieves strong performance across diverse node- and graph-level tasks on unseen datasets with new input features, without requiring architecture changes or retraining. These results point to a promising direction for input-agnostic, transferable graph models.
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models
ProGFM transfers graph knowledge across domains by learning a prototype bank of per-edge, per-dimension propagation strengths and using them to modulate message passing on unseen graphs.