Preserving Geometric Integrity in Graph Prompting via Measure-Constrained Optimal Transport
Not on the map. Why?
Abstract (arXiv)
Graph prompt learning enables parameter-efficient adaptation of frozen Graph Neural Networks to downstream tasks through lightweight prompt parameters. As routing becomes increasingly node-adaptive, however, independently optimized local decisions can collectively concentrate assignment mass on a small subset of a finite shared prompt bank, even when individual node--prompt matches remain locally meaningful. We propose MINT (Measure-INtegrity Transport), an entropically regularized optimal transport framework that formulates node-to-prompt adaptation as a globally coupled allocation problem. The transport cost favors local geometric compatibility, while a prescribed prompt-side marginal explicitly controls graph-wide prompt utilization. We further derive an exact variance decomposition that separates prompt-side geometric variance into retained prompt-update variation and within-node barycentric dispersion, together with a conditional stability bound for the frozen-encoder forward map. Across standard citation networks and additional heterophilic graphs, MINT remains competitive in few-shot adaptation. Controlled and end-to-end experiments further distinguish the roles of routing and topology: fixed-marginal routing controls graph-wide prompt utilization and has measurable end-to-end effects on citation networks, while topology augmentation provides a complementary, graph-dependent mechanism for addressing structural mismatch. Code is available at https://github.com/Ga1axy0051/MINT.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 68 of its 82 references that are in the map. First posted on arXiv 20 Sep 2026.
Builds on
68 of 82 references.
References · 68
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2020Graph Contrastive Learning with Augmentationscited by 1,208
- 2018Deep Graph Infomaxcited by 1,106
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
- 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
- 2020Contrastive Multi-View Representation Learning on Graphscited by 652
38 more
- 2019Multi-scale Attributed Node Embeddingcited by 548
- 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
- 2017Word Translation Without Parallel Datacited by 487
- 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
- 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
- 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
- 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
- 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
- 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
- 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 186
- 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
- 2018Optimal Transport for structured data with application on graphscited by 172
- 2022Revisiting Heterophily For Graph Neural Networkscited by 169
- 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 167
- 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
- 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 148
- 2021From Canonical Correlation Analysis to Self-supervised Graph Neural Networkscited by 141
- 2023GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learnercited by 132
- 2019Gromov-Wasserstein Learning for Graph Matching and Node Embeddingcited by 126
- 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
- 2019Wasserstein Weisfeiler-Lehman Graph Kernelscited by 104
- 2020Graph Optimal Transport for Cross-Domain Alignmentcited by 103
- 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
- 2023PRODIGY: Enabling In-context Learning Over Graphscited by 98
- 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
- 2020Graph Prototypical Networks for Few-shot Learning on Attributed Networkscited by 90
- 2020Graph Meta Learning via Local Subgraphscited by 89
- 2022What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoderscited by 82
- 2019GOT: An Optimal Transport framework for Graph comparisoncited by 64
- 2025SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptationcited by 62
- 2024GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphscited by 58
- 2024GOFA: A Generative One-For-All Model for Joint Graph Language Modelingcited by 57
- 2020Wasserstein Embedding for Graph Learningcited by 56
- 2020The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxationcited by 56
- 2022Heterogeneous Graph Masked Autoencoderscited by 47
- 2023HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learningcited by 45
- 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
- 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 42
50 most cited of 68 All 68 (JSON)
Built on by
Not cited yet.