中文
相关论文

相关论文: Generalization Error of Graph Neural Networks in t…

200 篇论文

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our…

机器学习 · 计算机科学 2020-05-04 Melikasadat Emami , Mojtaba Sahraee-Ardakan , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

Graph neural networks (GNNs) are the most widely adopted model in graph-structured data oriented learning and representation. Despite their extraordinary success in real-world applications, understanding their working mechanism by theory is…

机器学习 · 计算机科学 2023-05-16 Huayi Tang , Yong Liu

We study the generalization capabilities of Message Passing Neural Networks (MPNNs), a prevalent class of Graph Neural Networks (GNN). We derive generalization bounds specifically for MPNNs with normalized sum aggregation and mean…

机器学习 · 计算机科学 2024-04-05 Sohir Maskey , Gitta Kutyniok , Ron Levie

Message passing neural networks (MPNN) have seen a steep rise in popularity since their introduction as generalizations of convolutional neural networks to graph-structured data, and are now considered state-of-the-art tools for solving a…

机器学习 · 计算机科学 2022-08-05 Sohir Maskey , Ron Levie , Yunseok Lee , Gitta Kutyniok

Graph Neural Networks (GNNs) extend convolutional neural networks to operate on graphs. Despite their impressive performances in various graph learning tasks, the theoretical understanding of their generalization capability is still…

机器学习 · 计算机科学 2025-06-10 Zhiyang Wang , Juan Cervino , Alejandro Ribeiro

Graph Neural Networks (GNNs) have become the standard method for learning from networks across fields ranging from biology to social systems, yet a principled understanding of what enables them to extract meaningful representations, or why…

机器学习 · 统计学 2026-03-19 Nil Ayday , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar

Graph Neural Networks (GNN) are currently the most popular approach for learning and prediction on graph-structured data and are deployed in various fields, from social network analysis to drug discovery. However, there is limited…

统计方法学 · 统计学 2026-05-26 Nil Ayday , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar

Graph neural networks are widely used tools for graph prediction tasks. Motivated by their empirical performance, prior works have developed generalization bounds for graph neural networks, which scale with graph structures in terms of the…

机器学习 · 计算机科学 2023-10-25 Haotian Ju , Dongyue Li , Aneesh Sharma , Hongyang R. Zhang

Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very…

机器学习 · 计算机科学 2019-11-28 Yuan Cao , Quanquan Gu

The primary objective of learning methods is generalization. Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the significant attribute that over-parameterized models in deep…

机器学习 · 计算机科学 2025-03-07 Lijia Yu , Yibo Miao , Yifan Zhu , Xiao-Shan Gao , Lijun Zhang

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

机器学习 · 计算机科学 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

Over-parameterization and adaptive methods have played a crucial role in the success of deep learning in the last decade. The widespread use of over-parameterization has forced us to rethink generalization by bringing forth new phenomena,…

机器学习 · 统计学 2020-12-01 Vatsal Shah , Soumya Basu , Anastasios Kyrillidis , Sujay Sanghavi

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

机器学习 · 计算机科学 2022-10-03 Tianxiang Gao , Hongyang Gao

Traditionally, graph neural networks have been trained using a single observed graph. However, the observed graph represents only one possible realization. In many applications, the graph may encounter uncertainties, such as having…

机器学习 · 计算机科学 2024-10-10 See Hian Lee , Feng Ji , Kelin Xia , Wee Peng Tay

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

In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the…

机器学习 · 统计学 2020-03-25 Matt Emschwiller , David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

Recently, over-parameterized neural networks have been extensively analyzed in the literature. However, the previous studies cannot satisfactorily explain why fully trained neural networks are successful in practice. In this paper, we…

机器学习 · 计算机科学 2019-10-28 Cong Fang , Hanze Dong , Tong Zhang

We study gradient-based regularization methods for neural networks. We mainly focus on two regularization methods: the total variation and the Tikhonov regularization. Applying these methods is equivalent to using neural networks to solve…

机器学习 · 计算机科学 2022-11-09 Lingfeng Li , Xue-Cheng Tai , Jiang Yang

We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, in the regime where the size of the layers is commensurate with the number of samples in the training data. We show that…

机器学习 · 统计学 2022-07-08 Inbar Seroussi , Ofer Zeitouni

Recently, significant progress has been made in understanding the generalization of neural networks (NNs) trained by gradient descent (GD) using the algorithmic stability approach. However, most of the existing research has focused on…

机器学习 · 计算机科学 2025-07-22 Puyu Wang , Yunwen Lei , Di Wang , Yiming Ying , Ding-Xuan Zhou
‹ 上一页 1 2 3 10 下一页 ›