SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning
For practitioners dealing with high-volume, evolving data streams and limited labels, SLeDGe offers a significant accuracy improvement over existing methods.
SLeDGe tackles semi-supervised learning on evolving data streams with scarce labels by jointly learning a predictive model and an adaptive graph structure. It achieves average relative accuracy gains of 31.7% with 0.1% labels and 14.8% with 1% labels across 12 datasets.
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.