Alimama Tech
Nov 22, 2023 · Artificial Intelligence
Robust Link Prediction under Bilateral Edge Noise via Robust Graph Information Bottleneck (RGIB)
The paper introduces Robust Graph Information Bottleneck (RGIB), a framework that jointly mitigates bilateral edge noise in link prediction by decoupling topology, label, and representation information, with two variants (RGIB‑SSL and RGIB‑REP) that achieve up to 12.9% AUC gains on benchmarks and have already boosted click‑through‑rate robustness and revenue in Alibaba’s advertising system.
Graph Neural NetworksRGIBbilateral noise
0 likes · 13 min read