aiqbench analysis
This paper introduces a fractional heat-kernel framework for semi-supervised graph learning that effectively mitigates oversmoothing by utilizing sustained label information within the Laplacian null space. The method demonstrates significant accuracy gains over standard Graph Attention Networks (GAT) in low-label regimes, particularly on benchmark datasets like Cora and CiteSeer with minimal training data.
Fractional Heat Kernel for Semi-Supervised Graph Learning with Small Training Sample Size
arXiv:2510.04440v2 Announce Type: replace Abstract: We develop a source-driven fractional heat-kernel framework for semi-super\-vised graph learning that combines nonlocal propagation with sustained label information. A fixed nonzero label source compatible with the Laplacian null space prevents asymptotic collapse into that space, providing a mechanism for mitigating oversmoothing at long diffusion times. The fractional order controls the relative modal attenuation and the spectral weighting of the sustained response, while the diffusion time sets the propagation horizon. We characterize conservation laws and equilibria on normalized and disconnected graphs, develop a null-space deflation, and analyze the approximation of the propagators. On Two-Moon, fractional orders improve source-free propagation, while compatible source-driven diffusion exceeds $96\%$ mean accuracy with one training label per class at orders $0.8$ and $1$. On Cora and CiteSeer, the source-driven pipeline improves mean accuracy over GAT by $9.2$ and $8.0$ percentage points at one training label per class, with model selection on $500$ labeled validation nodes and closely comparable classical and fractional pipeline configurations; it matches GAT on PubMed and trails it at ten and twenty labels per class on Cora. Within GraphHeat, validation-based exponent selection at a common diffusion time yields a paired gain of $1.45$ percentage points at one label per class.
Abstract:We develop a source-driven fractional heat-kernel framework for semi-super\-vised graph learning that combines nonlocal propagation with sustained label information. A fixed nonzero label source compatible with the Laplacian null space prevents asymptotic collapse into that space, providing a mechanism for mitigating oversmoothing at long diffusion times. The fractional order controls the relative modal attenuation and the spectral weighting of the sustained response, while the diffusion time sets the propagation horizon. We characterize conservation laws and equilibria on normalized and disconnected graphs, develop a null-space deflation, and analyze the approximation of the propagators. On Two-Moon, fractional orders improve source-free propagation, while compatible source-driven diffusion exceeds $96\%$ mean accuracy with one training label per class at orders $0.8$ and $1$. On Cora and CiteSeer, the source-driven pipeline improves mean accuracy over GAT by $9.2$ and $8.0$ percentage points at one training label per class, with model selection on $500$ labeled validation nodes and closely comparable classical and fractional pipeline configurations; it matches GAT on PubMed and trails it at ten and twenty labels per class on Cora. Within GraphHeat, validation-based exponent selection at a common diffusion time yields a paired gain of $1.45$ percentage points at one label per class.
Machine Learning (cs.LG)
arXiv:2510.04440 [cs.LG]
(or arXiv:2510.04440v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2510.04440 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 290 words
Related coverage
Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learning
arXiv · Sep 16, 2026
Learning Spectral Allocation: A Fractional Diffusion Framework for Adaptive Volumetric Segmentation
arXiv · Sep 24, 2026
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · Jul 15, 2026
Federated Semi-Supervised Graph Neural Networks with Prototype-Guided Pseudo-Labeling for Privacy-Preserving Gestational Diabetes Mellitus Prediction
arXiv · Sep 30, 2026