Publications Repository - Helmholtz-Zentrum Dresden-Rossendorf
1 PublicationFully Linear Graph Convolutional Networks for Semi-Supervised and Unsupervised Classification
Cai, Y.; Zhang, Z.; Ghamisi, P.; Cai, Z.; Liu, X.; Ding, Y.
Abstract
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.
-
ACM Transactions on Intelligent Systems and Technology 14(2023)3, 40
DOI: 10.1145/3579828
Cited 5 times in Scopus
Downloads
- Open Access Version from arxiv.org
- Secondary publication expected
Permalink: https://www.hzdr.de/publications/Publ-37887
Years: 2023 2022 2021 2020 2019 2018 2017 2016 2015