English
Related papers

Related papers: Tackling Over-Smoothing for General Graph Convolut…

200 papers

Current Graph Neural Networks (GNNs) suffer from the over-smoothing problem, which results in indistinguishable node representations and low model performance with more GNN layers. Many methods have been put forward to tackle this problem…

Machine Learning · Computer Science 2022-10-25 Xinshun Feng , Herun Wan , Shangbin Feng , Hongrui Wang , Jun Zhou , Qinghua Zheng , Minnan Luo

Clustering techniques attempt to group objects with similar properties into a cluster. Clustering the nodes of an attributed graph, in which each node is associated with a set of feature attributes, has attracted significant attention.…

Computer Vision and Pattern Recognition · Computer Science 2020-09-15 Chaojie Ji , Hongwei Chen , Ruxin Wang , Yunpeng Cai , Hongyan Wu

Oversmoothing is a central challenge of building more powerful Graph Neural Networks (GNNs). While previous works have only demonstrated that oversmoothing is inevitable when the number of graph convolutions tends to infinity, in this…

Machine Learning · Computer Science 2023-03-02 Xinyi Wu , Zhengdao Chen , William Wang , Ali Jadbabaie

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

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).…

Implicit Graph Neural Networks (GNNs) have achieved significant success in addressing graph learning problems recently. However, poorly designed implicit GNN layers may have limited adaptability to learn graph metrics, experience…

Machine Learning · Computer Science 2024-02-16 Guoji Fu , Mohammed Haroon Dupty , Yanfei Dong , Lee Wee Sun

Graph Convolution Networks (GCNs) manifest great potential in recommendation. This is attributed to their capability on learning good user and item embeddings by exploiting the collaborative signals from the high-order neighbors. Like other…

Information Retrieval · Computer Science 2021-03-30 Fan Liu , Zhiyong Cheng , Lei Zhu , Zan Gao , Liqiang Nie

Graph neural networks (GNNs) have achieved strong performance across various real-world domains. Nevertheless, they suffer from oversquashing, where long-range information is distorted as it is compressed through limited message-passing…

Machine Learning · Computer Science 2026-04-03 Tanvir Hossain , Muhammad Ifte Khairul Islam , Lilia Chebbah , Charles Fanning , Esra Akbas

Graph Neural Networks (GNNs) have emerged as the most powerful weapon for various graph tasks due to the message-passing mechanism's great local information aggregation ability. However, over-smoothing has always hindered GNNs from going…

Machine Learning · Computer Science 2024-03-26 Yundong Sun , Dongjie Zhu , Yansong Wang , Zhaoshuo Tian

Deep graph neural networks (GNNs) often suffer from oversmoothing, where node representations become overly homogeneous with increasing depth. While techniques like normalization, residual connections, and edge dropout have been proposed to…

Machine Learning · Computer Science 2025-05-30 Jiaqi Wang , Xinyi Wu , James Cheng , Yifei Wang

Graph neural networks (GNNs) are one of the most popular research topics for deep learning. GNN methods typically have been designed on top of the graph signal processing theory. In particular, diffusion equations have been widely used for…

Machine Learning · Computer Science 2023-06-16 Jeongwhan Choi , Seoyoung Hong , Noseong Park , Sung-Bae Cho

With the tremendous success of Graph Convolutional Networks (GCNs), they have been widely applied to recommender systems and have shown promising performance. However, most GCN-based methods rigorously stick to a common GCN learning…

Information Retrieval · Computer Science 2022-09-07 Shaowen Peng , Kazunari Sugiyama , Tsunenori Mine

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

Residual connections and normalization layers have become standard design choices for graph neural networks (GNNs), and were proposed as solutions to the mitigate the oversmoothing problem in GNNs. However, how exactly these methods help…

Machine Learning · Computer Science 2026-01-21 Michael Scholkemper , Xinyi Wu , Ali Jadbabaie , Michael T. Schaub

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

While Graph Neural Networks (GNNs) have been successfully leveraged for learning on graph-structured data across domains, several potential pitfalls have been described recently. Those include the inability to accurately leverage…

Machine Learning · Computer Science 2024-03-21 Lukas Fesser , Melanie Weber

The relationship between Layer Normalization (LN) placement and the oversmoothing phenomenon remains underexplored. We identify a critical dilemma: Pre-LN architectures avoid oversmoothing but suffer from the curse of depth, while Post-LN…

Machine Learning · Computer Science 2025-12-11 Weiqi Guan , Junlin He

State-of-the-art Graph Neural Networks (GNNs) have limited scalability with respect to the graph and model sizes. On large graphs, increasing the model depth often means exponential expansion of the scope (i.e., receptive field). Beyond…

Despite Graph neural networks' significant performance gain over many classic techniques in various graph-related downstream tasks, their successes are restricted in shallow models due to over-smoothness and the difficulties of…

Machine Learning · Computer Science 2023-12-15 Jin Li , Qirong Zhang , Shuling Xu , Xinlong Chen , Longkun Guo , Yang-Geng Fu
‹ Prev 1 3 4 5 6 7 10 Next ›