Weak Supervision for Real World Graphs
This addresses label scarcity and noise in high-stakes domains like human trafficking detection and misinformation monitoring, representing a novel method for a known bottleneck.
The paper tackles node classification in real-world graphs with label scarcity and noise by proposing WSNET, a weakly supervised graph contrastive learning framework that leverages weak signals, achieving up to 15% F1 score improvement over state-of-the-art methods.
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.