# GLAM: Graph Learning by Modeling Affinity to Labeled Nodes for Graph Neural Networks

arXiv: https://arxiv.org/abs/2102.10403 · HTML: https://mlsanity.com/paper/2102.10403/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 20 Feb 2021.

## Builds on (most cited first, 20 of 20)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [Learning Discrete Structures for Graph Neural Networks](https://mlsanity.com/paper/1903.11960/) (2019)
- [Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings](https://mlsanity.com/paper/2006.13009/) (2020)
- [NetGAN: Generating Graphs via Random Walks](https://mlsanity.com/paper/1803.00816/) (2018)
- [Bayesian graph convolutional neural networks for semi-supervised classification](https://mlsanity.com/paper/1811.11103/) (2018)
- [Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning](https://mlsanity.com/paper/1905.01102/) (2019)
- [Graph-Revised Convolutional Network](https://mlsanity.com/paper/1911.07123/) (2019)
- [A Flexible Generative Framework for Graph-based Semi-supervised Learning](https://mlsanity.com/paper/1905.10769/) (2019)
- [HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2008.12842/) (2020)
- [A Quest for Structure: Jointly Learning the Graph Structure and Semi-Supervised Classification](https://mlsanity.com/paper/1909.12385/) (2019)
- [GraphOpt: Learning Optimization Models of Graph Formation](https://mlsanity.com/paper/2007.03619/) (2020)

## Built on by (most cited first, 2 of 2)

- [Robust Graph Structure Learning under Heterophily](https://mlsanity.com/paper/2403.03659/) (2024)
- [DynLP: Parallel Dynamic Batch Update for Label Propagation in Semi-Supervised Learning](https://mlsanity.com/paper/2604.06596/) (2026)

## Abstract (arXiv)

Graph Neural Networks have shown excellent performance on semi-supervised classification tasks. However, they assume access to a graph that may not be often available in practice. In the absence of any graph, constructing k-Nearest Neighbor (kNN) graphs from the given data have shown to give improvements when used with GNNs over other semi-supervised methods. This paper proposes a semi-supervised graph learning method for cases when there are no graphs available. This method learns a graph as a convex combination of the unsupervised kNN graph and a supervised label-affinity graph. The label-affinity graph directly captures all the nodes' label-affinity with the labeled nodes, i.e., how likely a node has the same label as the labeled nodes. This affinity measure contrasts with the kNN graph where the metric measures closeness in the feature space. Our experiments suggest that this approach gives close to or better performance (up to 1.5%), while being simpler and faster (up to 70x) to train, than state-of-the-art graph learning methods. We also conduct several experiments to highlight the importance of individual components and contrast them with state-of-the-art methods.