中文
相关论文

相关论文: Generalization of Geometric Graph Neural Networks …

200 篇论文

Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to…

机器学习 · 计算机科学 2019-11-14 Michael Lingzhi Li , Meng Dong , Jiawei Zhou , Alexander M. Rush

Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we…

机器学习 · 计算机科学 2019-10-30 Qi Liu , Maximilian Nickel , Douwe Kiela

Graph neural networks (GNNs) have become powerful tools for processing graph-based information in various domains. A desirable property of GNNs is transferability, where a trained network can swap in information from a different graph…

机器学习 · 计算机科学 2024-06-24 A. Martina Neuman , Jason J. Bramburger

Hypergraph neural networks have been promising tools for handling learning tasks involving higher-order data, with notable applications in web graphs, such as modeling multi-way hyperlink structures and complex user interactions. Yet, their…

机器学习 · 计算机科学 2025-01-28 Yifan Wang , Gonzalo R. Arce , Guangmo Tong

Graph neural networks (GNNs) can process graphs of different sizes, but their ability to generalize across sizes, specifically from small to large graphs, is still not well understood. In this paper, we identify an important type of data…

机器学习 · 计算机科学 2021-07-19 Gilad Yehudai , Ethan Fetaya , Eli Meirom , Gal Chechik , Haggai Maron

In this work, we develop new generalization bounds for neural networks trained on data supported on Riemannian manifolds. Existing generalization theories often rely on complexity measures derived from Euclidean geometry, which fail to…

机器学习 · 计算机科学 2025-07-08 Krisanu Sarkar

Graph neural networks (GNNs) have been applied into a variety of graph tasks. Most existing work of GNNs is based on the assumption that the given graph data is optimal, while it is inevitable that there exists missing or incomplete edges…

机器学习 · 计算机科学 2022-05-13 Qianggang Ding , Deheng Ye , Tingyang Xu , Peilin Zhao

Current graph neural networks (GNNs) lack generalizability with respect to scales (graph sizes, graph diameters, edge weights, etc..) when solving many graph analysis problems. Taking the perspective of synthesizing graph theory programs,…

机器学习 · 计算机科学 2020-10-27 Hao Tang , Zhiao Huang , Jiayuan Gu , Bao-Liang Lu , Hao Su

Using message-passing graph neural networks (MPNNs) for node and link prediction is crucial in various scientific and industrial domains, which has led to the development of diverse MPNN architectures. Besides working well in practical…

机器学习 · 计算机科学 2025-10-31 Antonis Vasileiou , Timo Stoll , Christopher Morris

While Graph Neural Networks (GNNs) are powerful models for learning representations on graphs, most state-of-the-art models do not have significant accuracy gain beyond two to three layers. Deep GNNs fundamentally need to address: 1).…

Graph neural networks (GNNs) are powerful machine learning models for various graph learning tasks. Recently, the limitations of the expressive power of various GNN models have been revealed. For example, GNNs cannot distinguish some…

机器学习 · 计算机科学 2021-01-19 Ryoma Sato , Makoto Yamada , Hisashi Kashima

Graph neural networks (GNNs) have achieved tremendous success on multiple graph-based learning tasks by fusing network structure and node features. Modern GNN models are built upon iterative aggregation of neighbor's/proximity features by…

机器学习 · 计算机科学 2021-06-15 Susheel Suresh , Vinith Budde , Jennifer Neville , Pan Li , Jianzhu Ma

Graph Neural Networks (GNNs) are powerful tools for learning on structured data, yet the relationship between their expressivity and predictive performance remains unclear. We introduce a family of premetrics that capture different degrees…

机器学习 · 计算机科学 2025-05-19 Sohir Maskey , Raffaele Paolino , Fabian Jogl , Gitta Kutyniok , Johannes F. Lutzeyer

Graph neural networks (GNNs) are composed of layers consisting of graph convolutions and pointwise nonlinearities. Due to their invariance and stability properties, GNNs are provably successful at learning representations from data…

机器学习 · 计算机科学 2023-08-09 Luana Ruiz , Luiz F. O. Chamon , Alejandro Ribeiro

Graph Neural Networks (GNNs) are powerful deep learning methods for Non-Euclidean data. Popular GNNs are message-passing algorithms (MPNNs) that aggregate and combine signals in a local graph neighborhood. However, shallow MPNNs tend to…

Graph representation learning has been widely studied and demonstrated effectiveness in various graph tasks. Most existing works embed graph data in the Euclidean space, while recent works extend the embedding models to hyperbolic or…

机器学习 · 计算机科学 2023-04-04 Cheng Deng , Fan Xu , Jiaxing Ding , Luoyi Fu , Weinan Zhang , Xinbing Wang

We propose a theoretical framework for training Graph Neural Networks (GNNs) on large input graphs via training on small, fixed-size sampled subgraphs. This framework is applicable to a wide range of models, including popular sampling-based…

机器学习 · 计算机科学 2023-10-18 Yeganeh Alimohammadi , Luana Ruiz , Amin Saberi

A theoretical performance analysis of the graph neural network (GNN) is presented. For classification tasks, the neural network approach has the advantage in terms of flexibility that it can be employed in a data-driven manner, whereas…

机器学习 · 计算机科学 2020-01-29 Tatsuro Kawamoto , Masashi Tsubaki , Tomoyuki Obuchi

Many real-world phenomena can be modeled as a graph, making them extremely valuable due to their ubiquitous presence. GNNs excel at capturing those relationships and patterns within these graphs, enabling effective learning and prediction…

机器学习 · 计算机科学 2023-11-28 Abhinav Raghuvanshi , Kushal Sokke Malleshappa

Interpreting graph neural networks (GNNs) is difficult because message passing mixes signals and internal channels rarely align with human concepts. We study superposition, the sharing of directions by multiple features, directly in the…

机器学习 · 计算机科学 2026-01-19 Lukas Pertl , Han Xuanyuan , Pietro Liò