中文
相关论文

相关论文: Beyond Over-smoothing: Uncovering the Trainability…

200 篇论文

Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However, on large-scale real-world graphs, GNNs face two major…

机器学习 · 计算机科学 2026-03-10 Xiang Li , Jianpeng Qi , Haobing Liu , Yuan Cao , Guoqing Chao , Zhongying Zhao , Junyu Dong , Xinwang Liu , Yanwei Yu

Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e.g., as can occur as a result of…

机器学习 · 计算机科学 2021-12-06 Yongyi Yang , Tang Liu , Yangkun Wang , Jinjing Zhou , Quan Gan , Zhewei Wei , Zheng Zhang , Zengfeng Huang , David Wipf

Graph Neural Networks (GNNs) have become powerful tools for learning from graph-structured data, finding applications across diverse domains. However, as graph sizes and connectivity increase, standard GNN training methods face significant…

机器学习 · 计算机科学 2025-12-01 Eshed Gal , Moshe Eliasof , Carola-Bibiane Schönlieb , Ivan I. Kyrchei , Eldad Haber , Eran Treister

We comment on Cai and Wang (2020, arXiv:2006.13318), who analyze over-smoothing in GNNs via Dirichlet energy. We show that under mild spectral conditions (including with Leaky-ReLU), the Dirichlet energy of node embeddings decreases…

机器学习 · 计算机科学 2025-09-05 Razi Hasson , Reuven Guetta

While Dirichlet energy serves as a prevalent metric for quantifying over-smoothing, it is inherently restricted to capturing first-order feature derivatives. To address this limitation, we propose a generalized family of node similarity…

机器学习 · 计算机科学 2025-12-09 Weiqi Guan , Zihao Shi

In this work, we generalize the ideas of Kaiming initialization to Graph Neural Networks (GNNs) and propose a new scheme (G-Init) that reduces oversmoothing, leading to very good results in node and graph classification tasks. GNNs are…

机器学习 · 计算机科学 2024-11-01 Dimitrios Kelesis , Dimitris Fotakis , Georgios Paliouras

Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. However, they suffer from the notorious over-smoothing problem, in which the learned representations of densely…

机器学习 · 计算机科学 2020-04-10 Xin Xin , Alexandros Karatzoglou , Ioannis Arapakis , Joemon M. Jose

Graph Neural Networks (GNNs) often perform better for high-degree nodes than low-degree nodes on node classification tasks. This degree bias can reinforce social marginalization by, e.g., privileging celebrities and other high-degree actors…

机器学习 · 计算机科学 2024-11-04 Arjun Subramonian , Jian Kang , Yizhou Sun

We present Gradient Gating (G$^2$), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing…

Our study reveals new theoretical insights into over-smoothing and feature over-correlation in graph neural networks. Specifically, we demonstrate that with increased depth, node representations become dominated by a low-dimensional…

机器学习 · 计算机科学 2024-09-19 Andreas Roth , Thomas Liebig

Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the…

机器学习 · 计算机科学 2019-10-29 Guangtao Wang , Rex Ying , Jing Huang , Jure Leskovec

Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A prevailing perspective in deep learning encourages using…

计算机视觉与模式识别 · 计算机科学 2023-10-27 Jinjin Gu , Xianzheng Ma , Xiangtao Kong , Yu Qiao , Chao Dong

Graph Neural Networks (GNNs) typically operate by message-passing, where the state of a node is updated based on the information received from its neighbours. Most message-passing models act as graph convolutions, where features are mixed…

Financial fraud is always a major problem in the field of finance, as it can cause significant consequences. As a result, many approaches have been designed to detect it, and lately Graph Neural Networks (GNNs) have been demonstrated as a…

机器学习 · 计算机科学 2026-01-13 Hoang Hiep Trieu

In this work we investigate an observation made by Kipf \& Welling, who suggested that untrained GCNs can generate meaningful node embeddings. In particular, we investigate the effect of training only a single layer of a GCN, while keeping…

机器学习 · 计算机科学 2024-10-18 Dimitrios Kelesis , Dimitris Fotakis , Georgios Paliouras

Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semisupervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local…

机器学习 · 计算机科学 2018-01-24 Qimai Li , Zhichao Han , Xiao-Ming Wu

Despite the enormous success of Graph Convolutional Networks (GCNs) in modeling graph-structured data, most of the current GCNs are shallow due to the notoriously challenging problems of over-smoothening and information squashing along with…

机器学习 · 计算机科学 2022-10-18 Ajay Jaiswal , Peihao Wang , Tianlong Chen , Justin F. Rousseau , Ying Ding , Zhangyang Wang

Graph neural networks are increasingly becoming the go-to approach in various fields such as computer vision, computational biology and chemistry, where data are naturally explained by graphs. However, unlike traditional convolutional…

机器学习 · 计算机科学 2021-10-28 Moshe Eliasof , Eldad Haber , Eran Treister

Graph Neural Network (GNN), with the main idea of encoding graph structure information of graphs by propagation and aggregation, has developed rapidly. It achieved excellent performance in representation learning of multiple types of graphs…

机器学习 · 计算机科学 2024-07-04 Yushan Zhu , Wen Zhang , Yajing Xu , Zhen Yao , Mingyang Chen , Huajun Chen

In the graph domain, deep graph networks based on Message Passing Neural Networks (MPNNs) or Graph Transformers often cause over-smoothing of node features, limiting their expressive capacity. Many upsampling techniques involving node and…

机器学习 · 计算机科学 2026-02-03 Xiaotang Wang , Yun Zhu , Haizhou Shi , Yongchao Liu , Yongqi Zhang