Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation
Zhi Li, Haowei Liu, Hongchen Yang +5
Adversarial robustness distillation typically treats a robust teacher as a fixed knowledge source and transfers robustness to a compact student in a one-way manner. This paradigm t…
cs.LG2026
ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes
Ziyan Wang, Liwen Wu, Cheng Xie +3
Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-world anomaly detection spanni…