English
Related papers

Related papers: A Survey on Oversmoothing in Graph Neural Networks

200 papers

Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph classification. However, it is…

Machine Learning · Computer Science 2021-10-19 Langzhang Liang , Cuiyun Gao , Shiyi Chen , Shishi Duan , Yu pan , Junjin Zheng , Lei Wang , Zenglin Xu

Graph Neural Networks (GNNs) set the state-of-the-art in representation learning for graph-structured data. They are used in many domains, from online social networks to complex molecules. Most GNNs leverage the message-passing paradigm and…

Machine Learning · Computer Science 2025-03-06 Tuğrul Hasan Karabulut , İnci M. Baytaş

Graph Neural Networks (GNNs) have achieved a lot of success on graph-structured data. However, it is observed that the performance of graph neural networks does not improve as the number of layers increases. This effect, known as…

Machine Learning · Computer Science 2020-06-25 Chen Cai , Yusu Wang

Oversmoothing is a common challenge in learning graph neural networks (GNN), where, as layers increase, embedding features learned from GNNs quickly become similar or indistinguishable, making them incapable of differentiating network…

Machine Learning · Computer Science 2025-07-22 Yufei Jin , Xingquan Zhu

Oversmoothing has long been identified as a major limitation of Graph Neural Networks (GNNs): input node features are smoothed at each layer and converge to a non-informative representation, if the weights of the GNN are sufficiently…

Machine Learning · Computer Science 2026-03-16 Nicolas Keriven

Graph Neural Networks (GNNs) have achieved promising performance on a wide range of graph-based tasks. Despite their success, one severe limitation of GNNs is the over-smoothing issue (indistinguishable representations of nodes in different…

Machine Learning · Computer Science 2019-11-19 Deli Chen , Yankai Lin , Wei Li , Peng Li , Jie Zhou , Xu Sun

Recent years have witnessed remarkable success achieved by graph neural networks (GNNs) in many real-world applications such as recommendation and drug discovery. Despite the success, oversmoothing has been identified as one of the key…

Machine Learning · Computer Science 2022-06-17 Wei Jin , Xiaorui Liu , Yao Ma , Charu Aggarwal , Jiliang Tang

Increasing the depth of GCN, which is expected to permit more expressivity, is shown to incur performance detriment especially on node classification. The main cause of this lies in over-smoothing. The over-smoothing issue drives the output…

Machine Learning · Computer Science 2022-07-12 Wenbing Huang , Yu Rong , Tingyang Xu , Fuchun Sun , Junzhou Huang

In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data. However, it is known that the performance of GCNs degrades with increasing…

Machine Learning · Computer Science 2022-11-29 Yujun Yan , Milad Hashemi , Kevin Swersky , Yaoqing Yang , Danai Koutra

Graph neural networks (GNNs) are widely used in domains like social networks and biological systems. However, the locality assumption of GNNs, which limits information exchange to neighboring nodes, hampers their ability to capture…

Machine Learning · Computer Science 2023-07-04 Tingting Dan , Jiaqi Ding , Ziquan Wei , Shahar Z Kovalsky , Minjeong Kim , Won Hwa Kim , Guorong Wu

It is known that the current graph neural networks (GNNs) are difficult to make themselves deep due to the problem known as over-smoothing. Multi-scale GNNs are a promising approach for mitigating the over-smoothing problem. However, there…

Machine Learning · Computer Science 2021-01-07 Kenta Oono , Taiji Suzuki

Graph Convolutional Networks (GCNs) are known to suffer from performance degradation as the number of layers increases, which is usually attributed to over-smoothing. Despite the apparent consensus, we observe that there exists a…

Machine Learning · Computer Science 2021-10-29 Weilin Cong , Morteza Ramezani , Mehrdad Mahdavi

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…

Machine Learning · Computer Science 2025-12-09 Weiqi Guan , Zihao Shi

Geometric deep learning has made great strides towards generalizing the design of structure-aware neural networks from traditional domains to non-Euclidean ones, giving rise to graph neural networks (GNN) that can be applied to…

Machine Learning · Statistics 2024-10-28 Frederik Wenkel , Yimeng Min , Matthew Hirn , Michael Perlmutter , Guy Wolf

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…

Machine Learning · Computer Science 2024-09-19 Andreas Roth , Thomas Liebig

Numerous recent research on graph neural networks (GNNs) has focused on formulating GNN architectures as an optimization problem with the smoothness assumption. However, in node classification tasks, the smoothing effect induced by GNNs…

Machine Learning · Computer Science 2023-09-14 Jiayu Zhai , Lequan Lin , Dai Shi , Junbin Gao

Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and…

Machine Learning · Computer Science 2026-05-05 Hugo Attali , Nathalie Pernelle , Davide Buscaldi , Fragkiskos D. Malliaros

Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and…

Machine Learning · Computer Science 2026-05-04 Hugo Attali , Davide Buscaldi , Nathalie Pernelle , Fragkiskos D. Malliaros

In designing and applying graph neural networks, we often fall into some optimization pitfalls, the most deceptive of which is that we can only build a deep model by solving over-smoothing. The fundamental reason is that we do not…

Machine Learning · Computer Science 2022-11-22 Xue Li , Yuanzhi Cheng

Graph convolutions have gained popularity due to their ability to efficiently operate on data with an irregular geometric structure. However, graph convolutions cause over-smoothing, which refers to representations becoming more similar…

Machine Learning · Computer Science 2024-09-04 Andreas Roth