中文
相关论文

相关论文: MeixnerNet: Adaptive and Robust Spectral Graph Neu…

200 篇论文

Spectral Graph Neural Networks (GNNs) suffer from two critical limitations: poor performance on "heterophilic" graphs and performance collapse at high polynomial degrees (K), known as over-smoothing. Both issues stem from the static,…

机器学习 · 计算机科学 2025-11-20 Huseyin Goksu

This paper aims to provide a novel design of a multiscale framelet convolution for spectral graph neural networks (GNNs). While current spectral methods excel in various graph learning tasks, they often lack the flexibility to adapt to…

机器学习 · 计算机科学 2024-07-30 Mengxi Yang , Dai Shi , Xuebin Zheng , Jie Yin , Junbin Gao

Recent advancements in Spectral Graph Convolutional Networks (SpecGCNs) have led to state-of-the-art performance in various graph representation learning tasks. To exploit the potential of SpecGCNs, we analyze corresponding graph filters…

机器学习 · 计算机科学 2024-12-03 Jie Zhang , Min-Te Sun

ChebNet, one of the earliest spectral GNNs, has largely been overshadowed by Message Passing Neural Networks (MPNNs), which gained popularity for their simplicity and effectiveness in capturing local graph structure. Despite their success,…

Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the…

机器学习 · 计算机科学 2024-03-13 Mingguo He , Zhewei Wei , Ji-Rong Wen

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-based methods to aggregate information, i.e., manually…

机器学习 · 计算机科学 2024-05-08 Mingguo He , Zhewei Wei , Shikun Feng , Zhengjie Huang , Weibin Li , Yu Sun , Dianhai Yu

Graph Neural Networks (GNNs) have achieved significant success across various domains by leveraging graph structures in data. Existing spectral GNNs, which use low-degree polynomial filters to capture graph spectral properties, may not…

机器学习 · 计算机科学 2025-05-09 Vahan Martirosyan , Jhony H. Giraldo , Fragkiskos D. Malliaros

Many representative graph neural networks, e.g., GPR-GNN and ChebNet, approximate graph convolutions with graph spectral filters. However, existing work either applies predefined filter weights or learns them without necessary constraints,…

机器学习 · 计算机科学 2022-02-07 Mingguo He , Zhewei Wei , Zengfeng Huang , Hongteng Xu

Mesh-based graph neural networks (GNNs) have become effective surrogates for PDE simulations, yet their deep message passing incurs high cost and over-smoothing on large, long-range meshes; hierarchical GNNs shorten propagation paths but…

机器学习 · 计算机科学 2025-09-16 Bo Lei , Victor M. Castillo , Yeping Hu

Spectral Graph Neural Networks (GNNs) operating in the canonical [-1, 1] domain (like ChebyNet and its adaptive generalization, L-JacobiNet) face a fundamental Flexibility-Stability Trade-off. Our previous work revealed a critical puzzle:…

信号处理 · 电气工程与系统科学 2025-11-19 Huseyin Goksu

Spectral Graph Neural Networks (GNNs) based on polynomial filters, such as ChebyNet, suffer from two critical limitations: 1) performance collapse on "heterophilic" graphs and 2) performance collapse at high polynomial degrees (K), known as…

机器学习 · 计算机科学 2025-11-20 Huseyin Goksu

Graph neural networks (GNNs) have recently been demonstrated to perform well on a variety of network-based tasks such as decentralized control and resource allocation, and provide computationally efficient methods for these tasks which have…

机器学习 · 计算机科学 2021-12-15 Raghu Arghal , Eric Lei , Shirin Saeedi Bidokhti

Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. However, these models tend to perform poorly on heterophilic graphs, where connected nodes have…

机器学习 · 计算机科学 2021-12-08 Vijay Lingam , Chanakya Ekbote , Manan Sharma , Rahul Ragesh , Arun Iyer , Sundararajan Sellamanickam

Graph Neural Networks (GNNs) are a promising deep learning approach for circumventing many real-world problems on graph-structured data. However, these models usually have at least one of four fundamental limitations: over-smoothing,…

机器学习 · 计算机科学 2022-10-03 Xun Liu , Alex Hay-Man Ng , Fangyuan Lei , Yikuan Zhang , Zhengmin Li

Graph Neural Networks (GNNs) based on spectral filters, such as the Adaptive Orthogonal Polynomial Filter (AOPF) class (e.g., LaguerreNet), have shown promise in unifying the solutions for heterophily and over-smoothing. However, these…

信号处理 · 电气工程与系统科学 2025-11-19 Huseyin Goksu

Designing spectral convolutional networks is a formidable task in graph learning. In traditional spectral graph neural networks (GNNs), polynomial-based methods are commonly used to design filters via the Laplacian matrix. In practical…

机器学习 · 计算机科学 2024-08-19 Gongpei Zhao , Tao Wang , Yi Jin , Congyan Lang , Yidong Li , Haibin Ling

Spectral Graph Neural Networks (GNNs) have achieved tremendous success in graph machine learning, with polynomial filters applied for graph convolutions, where all nodes share the identical filter weights to mine their local contexts.…

机器学习 · 计算机科学 2024-05-24 Jingwei Guo , Kaizhu Huang , Xinping Yi , Rui Zhang

Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such…

机器学习 · 计算机科学 2020-06-22 Luca Franceschi , Mathias Niepert , Massimiliano Pontil , Xiao He

Spectral Graph Neural Networks (GNNs) have achieved tremendous success in graph learning. As an essential part of spectral GNNs, spectral graph convolution extracts crucial frequency information in graph data, leading to superior…

机器学习 · 计算机科学 2024-04-09 Guoming Li , Jian Yang , Shangsong Liang , Dongsheng Luo

Spectral graph convolutional neural networks (GCNNs) have been producing encouraging results in graph classification tasks. However, most spectral GCNNs utilize fixed graphs when aggregating node features, while omitting edge feature…

计算机视觉与模式识别 · 计算机科学 2022-10-06 Yang Yi , Xuequan Lu , Shang Gao , Antonio Robles-Kelly , Yuejie Zhang
‹ 上一页 1 2 3 10 下一页 ›