利用噪声标签提升图数据分类，显著改善真实场景下的学习效果
Weak Supervision for Real World Graphs
- 设计对比学习框架，融合图结构、节点特征与多种噪声信号
- 在三个真实数据集上，F1得分最高比现有方法提升15%
- 适合标签稀缺且噪声多的高风险领域应用
真实世界图数据中的节点分类常面临标签稀缺和噪声问题，尤其在人类贩运检测与虚假信息监控等高风险领域。尽管直接监督有限，但这类图中往往存在多种弱信号——即不精确或间接的线索，仍可辅助学习。本文提出WSNET，一种新型弱监督图对比学习框架，通过针对弱标签数据定制的对比目标，整合图结构、节点特征及多个噪声监督源，实现鲁棒表征学习。在三个真实世界数据集与受控噪声的合成基准上，WSNET始终优于当前主流对比学习与噪声标签学习方法，F1得分最高提升15%。结果表明，弱监督下对比学习有效，利用不完美标签在图学习中具有广阔前景。
原文摘要 · Abstract (English)
Node classification in real world graphs often suffers from label scarcity and noise, especially in high stakes domains like human trafficking detection and misinformation monitoring. While direct supervision is limited, such graphs frequently contain weak signals, noisy or indirect cues, that can still inform learning. We propose WSNET, a novel weakly supervised graph contrastive learning framework that leverages these weak signals to guide robust representation learning. WSNET integrates graph structure, node features, and multiple noisy supervision sources through a contrastive objective tailored for weakly labeled data. Across three real world datasets and synthetic benchmarks with controlled noise, WSNET consistently outperforms state of the art contrastive and noisy label learning methods by up to 15% in F1 score. Our results highlight the effectiveness of contrastive learning under weak supervision and the promise of exploiting imperfect labels in graph based settings.
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。