# SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning

arXiv: https://arxiv.org/abs/2606.21096 · HTML: https://mlsanity.com/paper/2606.21096/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [How to learn a graph from smooth signals](https://mlsanity.com/paper/1601.02513/) (2016)
- [Towards Unsupervised Deep Graph Structure Learning](https://mlsanity.com/paper/2201.06367/) (2022)
- [Label-Efficient Online Continual Object Detection in Streaming Video](https://mlsanity.com/paper/2206.00309/) (2022)
- [Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments](https://mlsanity.com/paper/1810.07348/) (2018)
- [MN-DS: A Multilabeled News Dataset for News Articles Hierarchical Classification](https://mlsanity.com/paper/2212.12061/) (2022)
- [Uncertainty-Aware Graph Structure Learning](https://mlsanity.com/paper/2502.12618/) (2025)

## Abstract (arXiv)

Semi-supervised learning (SSL) on data streams is challenging due to the continuous evolution of high-volume data and the scarcity of labels. Existing methods are limited in leveraging the intrinsic relationships among samples because they typically rely on fixed similarity measures or static graph structures, which cannot capture how relationships evolve over time. We propose SLeDGe, an SSL method for data streams that jointly learns a predictive model and an adaptive graph structure under strict memory and label constraints. SLeDGe maintains compact labeled and unlabeled memories using distinct update strategies, balancing rapid adaptation to novel features with the retention of historical consistency. In addition, by encouraging sparsity in the relational graph, SLeDGe filters out spurious connections and enables effective propagation of label supervision. Across 12 datasets, SLeDGe outperforms state-of-the-art competitors, achieving average relative accuracy gains of 31.7% with 0.1% labels and 14.8% with 1% labels.