.png){kind=icon}
返回
Fully Linear Graph Convolutional Networks for Semi-Supervised and Unsupervised Classification
.png){kind=icon}
PRE
AI
DOI：10.1145/3579828.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This article presents FLGC, a simple yet effective fully linear graph convolutional network for semi-supervised and unsupervised learning. Instead of using gradient descent, we train FLGC based on computing a global optimal closed-form solution with a decoupled procedure, resulting in a generalized linear framework and making it easier to implement, train, and apply. We show that (1) FLGC is powerful to deal with both graph-structured data and regular data, (2) training graph convolutional models with closed-form solutions improve computational efficiency without degrading performance, and (3) FLGC acts as a natural generalization of classic linear models in the non-Euclidean domain (e.g., ridge regression and subspace clustering). Furthermore, we implement a semi-supervised FLGC and an unsupervised FLGC by introducing an initial residual strategy, enabling FLGC to aggregate long-range neighborhoods and alleviate over-smoothing. We compare our semi-supervised and unsupervised FLGCs against many state-of-the-art methods on a variety of classification and clustering benchmarks, demonstrating that the proposed FLGC models consistently outperform previous methods in terms of accuracy, robustness, and learning efficiency. The core code of our FLGC is released at https://github.com/AngryCai/FLGC.
Keyword:
Graph Convolutional Networks
linear model
Semi-Supervised Learning
subspace clustering
closed-form solution
期刊
IF:
6.6
论文数:
1.5K
被引数:
6.2K
机构
引用论文
Formylglycinamide Ribonucleotide Amidotransferase from Thermotoga maritima: Structural Insights into Complex Formation.png)
Biochemistry
OAAI
BiochemistryIF0
OAAI分享收藏Graph Convolutional Subspace Clustering: A Robust Subspace Clustering Framework for Hyperspectral Image图卷积子空间聚类: 高光谱图像鲁棒子空间聚类框架OAAI
OAAI分享收藏Tinnitus Retraining Therapy (TRT) as a Method for Treatment of Tinnitus and Hyperacusis Patients耳鸣再训练疗法 (TRT) 作为治疗耳鸣和高亢患者的方法
PREAI
分享收藏The changing epidemiology of paediatric brain tumours: a review from the Hospital for Sick Children
PREAI
分享收藏
查看更多内容