# Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport

arXiv: https://arxiv.org/abs/2203.10453 · HTML: https://mlsanity.com/paper/2203.10453/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Builds on (most cited first, 23 of 23)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Explicit Inductive Bias for Transfer Learning with Convolutional Networks](https://mlsanity.com/paper/1802.01483/) (2018)
- [Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration](https://mlsanity.com/paper/1705.09634/) (2017)
- [Gromov-Wasserstein Learning for Graph Matching and Node Embedding](https://mlsanity.com/paper/1901.06003/) (2019)
- [Self-supervised Graph-level Representation Learning with Local and Global Structure](https://mlsanity.com/paper/2106.04113/) (2021)
- [Graph Optimal Transport for Cross-Domain Alignment](https://mlsanity.com/paper/2006.14744/) (2020)
- [Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking](https://mlsanity.com/paper/2111.07786/) (2021)
- [DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks](https://mlsanity.com/paper/1901.09229/) (2019)
- [Wasserstein Contrastive Representation Distillation](https://mlsanity.com/paper/2012.08674/) (2020)
- [Improving Sequence-to-Sequence Learning via Optimal Transport](https://mlsanity.com/paper/1901.06283/) (2019)
- [Analyzing the Performance of Multilayer Neural Networks for Object Recognition](https://mlsanity.com/paper/1407.1610/) (2014)
- [Optimal Transport Graph Neural Networks](https://mlsanity.com/paper/2006.04804/) (2020)
- [Representation Transfer by Optimal Transport](https://mlsanity.com/paper/2007.06737/) (2020)

## Built on by (most cited first, 19 of 19)

- [GraphLoRA: Structure-Aware Contrastive Low-Rank Adaptation for Cross-Graph Transfer Learning](https://mlsanity.com/paper/2409.16670/) (2024)
- [Preventing Over-Smoothing for Hypergraph Neural Networks](https://mlsanity.com/paper/2203.17159/) (2022)
- [When to Pre-Train Graph Neural Networks? From Data Generation Perspective!](https://mlsanity.com/paper/2303.16458/) (2023)
- [A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation](https://mlsanity.com/paper/2410.19265/) (2024)
- [Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs](https://mlsanity.com/paper/2203.16939/) (2022)
- [Search to Fine-tune Pre-trained Graph Neural Networks for Graph-level Tasks](https://mlsanity.com/paper/2308.06960/) (2023)
- [Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns](https://mlsanity.com/paper/2312.13583/) (2023)
- [GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning](https://mlsanity.com/paper/2511.05592/) (2025)
- [A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective](https://mlsanity.com/paper/2403.16137/) (2024)
- [Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs](https://mlsanity.com/paper/2402.11153/) (2024)
- [SubGDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning](https://mlsanity.com/paper/2405.05665/) (2024)
- [A Simple Hypergraph Kernel Convolution based on Discounted Markov Diffusion Process](https://mlsanity.com/paper/2210.16884/) (2022)
- [Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications](https://mlsanity.com/paper/2303.13102/) (2023)
- [Enhancing Molecular Property Prediction with Auxiliary Learning and Task-Specific Adaptation](https://mlsanity.com/paper/2401.16299/) (2024)
- [GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning](https://mlsanity.com/paper/2406.13499/) (2024)
- [Graph Augmentation for Cross Graph Domain Generalization](https://mlsanity.com/paper/2502.18188/) (2025)
- [Graph Residual based Method for Molecular Property Prediction](https://mlsanity.com/paper/2408.03342/) (2024)
- [Bridging the Gap Between Simulated and Real Network Data Using Transfer Learning](https://mlsanity.com/paper/2510.00956/) (2025)
- [Locality-aware Private Class Identification for Domain Adaptation with Extreme Label Shift](https://mlsanity.com/paper/2605.05567/) (2026)

## Abstract (arXiv)

Recently, the pretrain-finetuning paradigm has attracted tons of attention in graph learning community due to its power of alleviating the lack of labels problem in many real-world applications. Current studies use existing techniques, such as weight constraint, representation constraint, which are derived from images or text data, to transfer the invariant knowledge from the pre-train stage to fine-tuning stage. However, these methods failed to preserve invariances from graph structure and Graph Neural Network (GNN) style models. In this paper, we present a novel optimal transport-based fine-tuning framework called GTOT-Tuning, namely, Graph Topology induced Optimal Transport fine-Tuning, for GNN style backbones. GTOT-Tuning is required to utilize the property of graph data to enhance the preservation of representation produced by fine-tuned networks. Toward this goal, we formulate graph local knowledge transfer as an Optimal Transport (OT) problem with a structural prior and construct the GTOT regularizer to constrain the fine-tuned model behaviors. By using the adjacency relationship amongst nodes, the GTOT regularizer achieves node-level optimal transport procedures and reduces redundant transport procedures, resulting in efficient knowledge transfer from the pre-trained models. We evaluate GTOT-Tuning on eight downstream tasks with various GNN backbones and demonstrate that it achieves state-of-the-art fine-tuning performance for GNNs.