SLeDGe让流数据半监督学习更高效，自动适应关系变化。
SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning
- 动态构建图结构，随数据流自适应更新样本关系。
- 用0.1%标签实现比顶尖方法高31.7%的准确率。
- 适合内存受限、标签稀缺的实时数据场景。
流数据的半监督学习因数据持续演化和标签稀缺而极具挑战。现有方法通常依赖固定相似度或静态图结构，难以捕捉关系随时间的变化。我们提出SLeDGe，一种在严格内存与标签约束下，联合学习预测模型与自适应图结构的流数据半监督学习方法。SLeDGe采用不同更新策略维护紧凑的有标签与无标签记忆，兼顾对新特征的快速适应与历史一致性保留。通过鼓励图结构稀疏化，有效过滤虚假连接，促进标签信息传播。在12个数据集上，SLeDGe显著优于现有最优方法：在仅使用0.1%标签时平均提升31.7%准确率，在1%标签时提升14.8%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。