# Structural Re-weighting Improves Graph Domain Adaptation

arXiv: https://arxiv.org/abs/2306.03221 · HTML: https://mlsanity.com/paper/2306.03221/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 61 references that are in the map.
- First posted on arXiv 5 Jun 2023.

## Builds on (most cited first, 30 of 33)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [Adversarial Graph Augmentation to Improve Graph Contrastive Learning](https://mlsanity.com/paper/2106.05819/) (2021)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism](https://mlsanity.com/paper/2201.12987/) (2022)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [G-Mixup: Graph Data Augmentation for Graph Classification](https://mlsanity.com/paper/2202.07179/) (2022)
- [Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2202.05441/) (2022)
- [GOOD: A Graph Out-of-Distribution Benchmark](https://mlsanity.com/paper/2206.08452/) (2022)
- [Contextual Stochastic Block Models](https://mlsanity.com/paper/1807.09596/) (2018)
- [Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift](https://mlsanity.com/paper/2003.04475/) (2020)
- [Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization](https://mlsanity.com/paper/2009.05204/) (2020)
- [Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data](https://mlsanity.com/paper/2108.01099/) (2021)
- [Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment](https://mlsanity.com/paper/1903.01689/) (2019)
- [Local Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2109.03856/) (2021)
- [DANE: Domain Adaptive Network Embedding](https://mlsanity.com/paper/1906.00684/) (2019)
- [Independence Promoted Graph Disentangled Networks](https://mlsanity.com/paper/1911.11430/) (2019)
- [Graph Domain Adaptation: A Generative View](https://mlsanity.com/paper/2106.07482/) (2021)

## Built on by (most cited first, 30 of 45)

- [Does Invariant Graph Learning via Environment Augmentation Learn Invariance?](https://mlsanity.com/paper/2310.19035/) (2023)
- [Rethinking Propagation for Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2402.05660/) (2024)
- [Graph Out-of-Distribution Generalization via Causal Intervention](https://mlsanity.com/paper/2402.11494/) (2024)
- [Pairwise Alignment Improves Graph Domain Adaptation](https://mlsanity.com/paper/2403.01092/) (2024)
- [GraphLoRA: Structure-Aware Contrastive Low-Rank Adaptation for Cross-Graph Transfer Learning](https://mlsanity.com/paper/2409.16670/) (2024)
- [Subgraph Pooling: Tackling Negative Transfer on Graphs](https://mlsanity.com/paper/2402.08907/) (2024)
- [A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation](https://mlsanity.com/paper/2410.19265/) (2024)
- [Beyond Message Passing: Neural Graph Pattern Machine](https://mlsanity.com/paper/2501.18739/) (2025)
- [Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics](https://mlsanity.com/paper/2505.12709/) (2025)
- [Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2412.11654/) (2024)
- [Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?](https://mlsanity.com/paper/2412.08174/) (2024)
- [Graph Domain Adaptation: Challenges, Progress and Prospects](https://mlsanity.com/paper/2402.00904/) (2024)
- [Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2407.11052/) (2024)
- [Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation](https://mlsanity.com/paper/2410.06976/) (2024)
- [Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning](https://mlsanity.com/paper/2508.00716/) (2025)
- [Can Modifying Data Address Graph Domain Adaptation?](https://mlsanity.com/paper/2407.19311/) (2024)
- [GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation](https://mlsanity.com/paper/2410.16606/) (2024)
- [GCAL: Adapting Graph Models to Evolving Domain Shifts](https://mlsanity.com/paper/2505.16860/) (2025)
- [Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs](https://mlsanity.com/paper/2402.11153/) (2024)
- [Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts](https://mlsanity.com/paper/2408.09490/) (2024)
- [Single Domain Generalization for Few-Shot Counting via Universal Representation Matching](https://mlsanity.com/paper/2505.16778/) (2025)
- [Degree-Conscious Spiking Graph for Cross-Domain Adaptation](https://mlsanity.com/paper/2410.06883/) (2024)
- [GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts](https://mlsanity.com/paper/2310.08677/) (2023)
- [Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptation](https://mlsanity.com/paper/2502.03033/) (2025)
- [Bridging Source and Target Domains via Link Prediction for Unsupervised Domain Adaptation on Graphs](https://mlsanity.com/paper/2505.24055/) (2025)
- [DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation](https://mlsanity.com/paper/2602.00656/) (2026)
- [Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation](https://mlsanity.com/paper/2602.10506/) (2026)
- [GeoMix: Towards Geometry-Aware Data Augmentation](https://mlsanity.com/paper/2407.10681/) (2024)
- [LinkThief: Combining Generalized Structure Knowledge with Node Similarity for Link Stealing Attack against GNN](https://mlsanity.com/paper/2410.02826/) (2024)
- [Gradual Domain Adaptation for Graph Learning](https://mlsanity.com/paper/2501.17443/) (2025)

## Abstract (arXiv)

In many real-world applications, graph-structured data used for training and testing have differences in distribution, such as in high energy physics (HEP) where simulation data used for training may not match real experiments. Graph domain adaptation (GDA) is a method used to address these differences. However, current GDA primarily works by aligning the distributions of node representations output by a single graph neural network encoder shared across the training and testing domains, which may often yield sub-optimal solutions. This work examines different impacts of distribution shifts caused by either graph structure or node attributes and identifies a new type of shift, named conditional structure shift (CSS), which current GDA approaches are provably sub-optimal to deal with. A novel approach, called structural reweighting (StruRW), is proposed to address this issue and is tested on synthetic graphs, four benchmark datasets, and a new application in HEP. StruRW has shown significant performance improvement over the baselines in the settings with large graph structure shifts, and reasonable performance improvement when node attribute shift dominates.