REVIEW 1 cited by
Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
read the original abstract
State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length. In this paper, we investigate the global structure of attention scores computed using this dot product mechanism on a typical distribution of inputs, and study the principal components of their variation. Through eigen analysis of full attention score matrices, as well as of their individual rows, we find that most of the variation among attention scores lie in a low-dimensional eigenspace. Moreover, we find significant overlap between these eigenspaces for different layers and even different transformer models. Based on this, we propose to compute scores only for a partial subset of token pairs, and use them to estimate scores for the remaining pairs. Beyond investigating the accuracy of reconstructing attention scores themselves, we investigate training transformer models that employ these approximations, and analyze the effect on overall accuracy. Our analysis and the proposed method provide insights into how to balance the benefits of exact pair-wise attention and its significant computational expense.
Forward citations
Cited by 1 Pith paper
-
Eigenvalues as a Metric for Memory Dynamics in Sequence Models
Eigenvalue spectra of attention and SSM dynamics show consistent signatures of memory retention and selective forgetting that align with task requirements.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.