arXiv Machine Learning
DimGrow: Memory-Efficient Field-level Embedding Dimension Search
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 2
LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems
arXiv:2606. 01111v1 Announce Type: new Abstract: Modern industrial recommender systems rely on thousands of heterogeneous features -- ranging from low-dimensional scalars (e.
arXiv Machine Learning
Jul 14
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
arXiv:2607. 11473v1 Announce Type: cross Abstract: In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware.
arXiv Machine Learning
Jun 5
FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
arXiv:2602. 02680v3 Announce Type: replace Abstract: The growing scale of deep neural networks, encompassing large language models (LLMs) and vision transformers (ViTs), has made training from scratch prohibitively expensive and deployment increasingly costly.
arXiv Computer Vision
3d ago
SOLAR: SVD-Optimized Lifelong Attention for Recommendation
arXiv:2603.02561v2 Announce Type: replace-cross Abstract: Attention mechanism remains the defining operator in Transformers since it provides expressive global credit assignment, yet its quadratic co...
arXiv AI
Jul 29
REPREC: Representation Driven Parameter-Efficient Recommendation System
arXiv:2607. 24845v1 Announce Type: cross Abstract: Large language models (LLMs) have been applied to sequential recommendation by formulating it as a natural language task.
arXiv AI
Jun 9
RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT
arXiv:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.