Dissecting the Diffusion Process in Linear Graph Convolutional Networks

2021-02-22 · NeurIPS 2021 12 · Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin

Graph Convolutional Networks (GCNs) have attracted more and more attentions in recent years. A typical GCN layer consists of a linear feature propagation step and a nonlinear transformation step. Recent works show that a linear GCN can achieve comparable performance to the original non-linear GCN while being much more computationally efficient. In this paper, we dissect the feature propagation steps of linear GCNs from a perspective of continuous graph diffusion, and analyze why linear GCNs fail to benefit from more propagation steps. Following that, we propose Decoupled Graph Convolution (DGC) that decouples the terminal time and the feature propagation steps, making it more flexible and capable of exploiting a very large number of feature propagation steps. Experiments demonstrate that our proposed DGC improves linear GCNs by a large margin and makes them competitive with many modern variants of non-linear GCNs.

📄 PDF Abstract BibTeX arXiv:2102.10739

Code (1)

yifeiwang77/dgc 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Bootstrapped Graph Diffusions: Exposing the Power of Nonlinearity

2017-03-07 · Eliav Buchnik, Edith Cohen

Graph-based semi-supervised learning (SSL) algorithms predict labels for all nodes based on provided labels of a small set of seed nodes. Classic methods capture the graph structure through some underlying diffusion proc…

Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs

2022-02-09 · Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain, Pietro Liò 외

Cellular sheaves equip graphs with a "geometrical" structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph with a trivial underlying sheaf. This cho…

Node Classification Node Classification on Non-Homophilic (Heterophilic) Graphs

Anisotropic Graph Convolutional Network for Semi-supervised Learning

2020-10-20 · Mahsa Mesgaran, A. Ben Hamza

Graph convolutional networks learn effective node embeddings that have proven to be useful in achieving high-accuracy prediction results in semi-supervised learning tasks, such as node classification. However, these netw…

Classification General Classification Node Classification

Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion

2025-11-17 · Cristina López Amado, Tassilo Schwarz, Yu Tian, Renaud Lambiotte arxiv

Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain limited by oversmoothing and poor performance on heterophilic graphs. To address these challenges, we introduce a…

HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification

2020-08-19 · Rahul Ragesh, Sundararajan Sellamanickam, Arun Iyer, Ram Bairi 외

We consider the problem of learning efficient and inductive graph convolutional networks for text classification with a large number of examples and features. Existing state-of-the-art graph embedding based methods such …

Classification General Classification Graph Embedding text-classification+1