Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs

Abstract

This paper focuses on the high computational complexity in Large Language Models (LLMs) a significant challenge in both natural language processing (NLP) and multi-modal tasks. We propose Low-Rank Approximation for Sparse At- tention (LoRA-Sparse) an innovative approach that strate- gically reduces this complexity. LoRA-Sparse introduces low-rank linear projection layers for sparse attention ap- proximation. It utilizes an order-mimic training methodol- ogy which is crucial for efficiently approximating the self- attention mechanism in LLMs. We empirically show that sparse attention not only reduces computational demands but also enhances model performance in both NLP and multi-modal tasks. This surprisingly shows that redundant attention in LLMs might be non-beneficial. We extensively validate LoRA-Sparse through rigorous empirical studies in both (NLP) and multi-modal tasks demonstrating its effec- tiveness and general applicability. Based on LLaMA and LLaVA models our methods can reduce more than half of the self-attention computation with even better performance than full-attention baselines.