Label Efficient Semi-Supervised Learning via Graph Filtering

By Qimai Li, Xiao-Ming Wu, 刘晗, Xiaotong Zhang, Zhichao Guan. 2019

179 citations recorded by the source corpus.

Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance. However, existing graph-based methods either are limited in their ability to jointly model graph structures and data features, such as the classical label propagation methods, or require a considerable amount of labeled data for training and validation due to high model complexity, such as the recent neural-network-based methods. In this paper, we address label efficient semi-supervised learning from a graph filtering perspective. Specifically, we propose a graph filtering framework that injects graph similarity into data features by taking them as signals on the graph and applying a low-pass graph filter to extract useful data representations for classification, where label efficiency can be achieved by conveniently adjusting the strength of the graph filter. Interestingly, this framework unifies two seemingly very different methods -- label propagation and graph convolutional networks. Revisiting them under the graph filtering framework leads to new insights that improve their modeling capabilities and reduce model complexity. Experiments on various semi-supervised classification tasks on four citation networks and one knowledge graph and one semi-supervised regression task for zero-shot image recognition validate our findings and proposals.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiao Wang
2. Chuan Shi
3. Tong Zhang
4. Yuhui Ding
5. Quanming Yao
6. Hao Zhu
7. Deyu Bo
8. Piotr Koniusz

In Information Systems

1. Xiao Wang
2. Chuan Shi
3. Hao Zhu
4. Deyu Bo
5. Piotr Koniusz
6. Huawei Shen
7. Quanming Yao
8. Tong Zhang

Citations in the corpus

• Simple Spectral Graph Convolution (2021, methodology): “The AR filter (Li et al., 2019) uses the regularized Laplacian kernel (Smola & Kondor, 2003) which differs from used by us (modified) Markov diffusion kernel.”
• Propagation Model Search for Graph Neural Networks (2020, methodology): “Second powers of  and Âs have also been employed by some GNN variants (Abu-El-Haija et al. 2019; Li et al. 2019; Wu et al. 2019) to represent longer distance propagation, and we add them to M.”
• Beyond Low-frequency Information in Graph Convolutional Networks (2021, methodology): “We compare FAGCN with two types of representative GNNs: Spectral-based methods, i.e., SGC (Wu et al. 2019), GCN (Kipf and Welling 2017), ChebNet (Defferrard, Bresson, and Vandergheynst 2016) and GWNN (Xu et al. 2019b); Spatial-based methods, i.e., GIN (Xu et al. 2019c), GAT (Velickovic et al. 2018),”