LGAIApr 22, 2022

Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention

arXiv:2204.10670v112 citationsh-index: 9
Originality Highly original
AI Analysis

This addresses the scalability and performance limitations of self-attention in neural modeling for long sequential data, offering a more efficient alternative.

The authors tackled the quadratic computational cost and low-rank bottleneck of dot-product self-attention by proposing Paramixer, a method that factorizes the interaction matrix into sparse matrices parameterized by MLPs, achieving O(N log N) cost and full-rank matrices, with experimental results showing better performance than state-of-the-art attention networks on most tasks.

Self-Attention is a widely used building block in neural modeling to mix long-range data elements. Most self-attention neural networks employ pairwise dot-products to specify the attention coefficients. However, these methods require $O(N^2)$ computing cost for sequence length $N$. Even though some approximation methods have been introduced to relieve the quadratic cost, the performance of the dot-product approach is still bottlenecked by the low-rank constraint in the attention matrix factorization. In this paper, we propose a novel scalable and effective mixing building block called Paramixer. Our method factorizes the interaction matrix into several sparse matrices, where we parameterize the non-zero entries by MLPs with the data elements as input. The overall computing cost of the new building block is as low as $O(N \log N)$. Moreover, all factorizing matrices in Paramixer are full-rank, so it does not suffer from the low-rank bottleneck. We have tested the new method on both synthetic and various real-world long sequential data sets and compared it with several state-of-the-art attention networks. The experimental results show that Paramixer has better performance in most learning tasks.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes