Hierarchical and Permutation-Invariant Feature Transformation Learning via Policy-Guided Embedding Search
This work proposes a framework with two complementary components: a permutation-invariant hierarchical module that captures interactions across features, operations, and abstraction levels, with a self-attention pooling mechanism that maps semantically equivalent structures to consistent embeddings aligned with downstr...
Rui Liu, Tao Zhe, Yanyong Huang et al.
· 2 citations