paper-with-me

홈 › Papers

Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability

2023-09-01 · Zehao Dong, Muhan Zhang, Philip R. O. Payne, Michael A Province, Carlos Cruchaga, Tianyu Zhao, Fuhai Li, Yixin Chen

The expressivity of Graph Neural Networks (GNNs) has been studied broadly in recent years to reveal the design principles for more powerful GNNs. Graph canonization is known as a typical approach to distinguish non-isomorphic graphs, yet rarely adopted when developing expressive GNNs. This paper proposes to maximize the expressivity of GNNs by graph canonization, then the power of such GNNs is studies from the perspective of model stability. A stable GNN will map similar graphs to close graph representations in the vectorial space, and the stability of GNNs is critical to generalize their performance to unseen graphs. We theoretically reveal the trade-off of expressivity and stability in graph-canonization-enhanced GNNs. Then we introduce a notion of universal graph canonization as the general solution to address the trade-off and characterize a widely applicable sufficient condition to solve the universal graph canonization. A comprehensive set of experiments demonstrates the effectiveness of the proposed method. In many popular graph benchmark datasets, graph canonization successfully enhances GNNs and provides highly competitive performance, indicating the capability and great potential of proposed method in general graph representation learning. In graph datasets where the sufficient condition holds, GNNs enhanced by universal graph canonization consistently outperform GNN baselines and successfully improve the SOTA performance up to $31\%$, providing the optimal solution to numerous challenging real-world graph analytical tasks like gene network representation learning in bioinformatics.

📄 PDF Abstract BibTeX arXiv:2309.00738

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Representation LearningRepresentation Learning

Similar Papers 제목 키워드 기반

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding

2023-10-28 · NeurIPS 2023 11 · Jiangyan Ma, Yifei Wang, Yisen Wang

Spectral embedding is a powerful graph embedding technique that has received a lot of attention recently due to its effectiveness on Graph Transformers. However, from a theoretical perspective, the universal expressive p…

Graph ClassificationGraph EmbeddingGraph Regression

When and How to Canonize: A Generalization Perspective

2026-05-10 · Yonatan Sverdlov, Benjamin Friedman, Snir Hordan, Nadav Dym arxiv

While invariant architectures are standard for processing symmetric data, there is growing interest in achieving invariance by applying group averaging or canonization to non-invariant backbones. However, the theoretical…

Casting graph isomorphism as a point set registration problem using a simplex embedding and sampling

2021-11-15 · Yigit Oktar

Graph isomorphism is an important problem as its worst-case time complexity is not yet fully understood. In this study, we try to draw parallels between a related optimization problem called point set registration. A gra…

Optimizing Explanations by Network Canonization and Hyperparameter Search

2022-11-30 · Frederik Pahde, Galip Ümit Yolcu, Alexander Binder, Wojciech Samek 외

Explainable AI (XAI) is slowly becoming a key component for many AI applications. Rule-based and modified backpropagation XAI approaches however often face challenges when being applied to modern model architectures incl…

Explainable Artificial Intelligence (XAI)image-classificationImage ClassificationQuestion Answering+2

Measurably Stronger Explanation Reliability via Model Canonization

2022-02-14 · Franz Motzkus, Leander Weber, Sebastian Lapuschkin

While rule-based attribution methods have proven useful for providing local explanations for Deep Neural Networks, explaining modern and more varied network architectures yields new challenges in generating trustworthy e…

model