LeAP is a model-agnostic plug-in that learns to permute and rank heterogeneous sparse features for selection, achieving SOTA on public datasets and removing over 3600 redundant features in a production system with 12k features.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
citing papers explorer
-
LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems
LeAP is a model-agnostic plug-in that learns to permute and rank heterogeneous sparse features for selection, achieving SOTA on public datasets and removing over 3600 redundant features in a production system with 12k features.
- ShuffleGate: Scalable Feature Optimization for Recommender Systems via Batch-wise Sensitivity Learning