Search papers, labs, and topics across Lattice.
This paper introduces SliGFM, a novel Graph Foundation Model that addresses the challenges of heterogeneous node features in graph learning by employing a topology-aware sliding-window feature encoding approach. The model is designed to unify diverse graph features while ensuring that the semantic information is preserved and transferable across different domains. Key findings reveal that SliGFM effectively captures relational patterns among features, outperforming existing methods in cross-domain knowledge transfer while maintaining the integrity of the original data semantics.
SliGFM achieves a breakthrough in graph learning by ensuring that heterogeneous features are not only unified but also semantically rich and transferable across domains.
Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for general-purpose graph learning, aiming to learn reusable knowledge that generalizes across diverse graph domains and downstream tasks, reducing the need for specific model development. Achieving this goal requires reconciling the substantial heterogeneity in node features, graph structures, and semantic information across domains. Among them, heterogeneous node features constitute a fundamental input-level barrier, as their dimensionality and semantics vary substantially across datasets. Existing studies typically project or map heterogeneous node features into a fixed-dimensional space, often implicitly equating dimensional uniformity with effective feature unification. Yet dimensional consistency alone does not ensure that the unified features preserve informative semantics and capture transferable patterns that can support cross-domain knowledge transfer. To bridge this conceptual gap, we distill four desiderata for cross-domain graph feature unification: formal uniformity, cross-domain transferability, information preservation, and backbone compatibility. Guided by these principles, we propose SliGFM, a graph foundation model built upon topology-aware sliding-window feature encoding and generative reconstruction. SliGFM orders feature dimensions by topological smoothness and scans the reordered features with a shared sliding-window feature encoder, transforming heterogeneous features into a common space of ordered fixed-dimensional feature tokens. This formulation enables a smoothness-aware transformer to capture transferable relational patterns among feature tokens within each node, while the generative reconstruction objective encourages preservation of the original feature information.
