5 papers
LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems
Yihong Huang, Chen Chu, Fei Chen +3
Modern industrial recommender systems rely on thousands of heterogeneous features -- ranging from low-dimensional scalars (e.g., statistical value) to high-dimensional embeddings (…
ShuffleGate: Scalable Feature Optimization for Recommender Systems via Batch-wise Sensitivity Learning
Yihong Huang, Chen Chu, Fan Zhang +4
Feature optimization -- specifically Feature Selection (FS) and Dimension Selection (DS) -- is critical for the efficiency and generalization of large-scale recommender systems. Wh…
DimGrow: Memory-Efficient Field-level Embedding Dimension Search
Yihong Huang, Chen Chu
Key feature fields need bigger embedding dimensionality, others need smaller. This demands automated dimension allocation. Existing approaches, such as pruning or Neural Architectu…
GradStop: Exploring Training Dynamics in Unsupervised Outlier Detection through Gradient
Yuang Zhang, Liping Wang, Yihong Huang +3
Unsupervised Outlier Detection (UOD) is a critical task in data mining and machine learning, aiming to identify instances that significantly deviate from the majority. Without any…
EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropy
Yihong Huang, Yuang Zhang, Liping Wang +2
Unsupervised Outlier Detection (UOD) is an important data mining task. With the advance of deep learning, deep Outlier Detection (OD) has received broad interest. Most deep UOD mod…