SIGMA: SHAP-Guided Implicit-Trajectory Generation for Metadata-Free LLM-Based AutoFE
This work proposes a SHAP-enhanced Implicit-trajectory Generation for Metadata-free AutoFE (SIGMA), a scalable constant-context optimization framework that leverages SHAP values to provide task-aware signals for guiding group feature generation instead of semantic information.
Xu Zheng, Kento Uchida, Shinichi Shirakawa
· 0 citations