Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and Clustering

Abstract

This paper 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.

arXiv commentUnder review by IEEE Trans. xxx

References in corpus (11)

• Graph Neural Networks: A Review of Methods and Applications
• Simplifying Graph Convolutional Networks
• Variational Graph Auto-Encoders
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• BS-Nets: An End-to-End Framework For Band Selection of Hyperspectral Image
• Exact Combinatorial Optimization with Graph Convolutional Neural Networks
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• End to end learning and optimization on graphs
• A Flexible Generative Framework for Graph-based Semi-supervised Learning
• Interpreting and Unifying Graph Neural Networks with An Optimization Framework