Pith. sign in

REVIEW

PairConnect: A Compute-Efficient MLP Alternative to Attention

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

arxiv 2106.08235 v1 pith:QFROUTNU submitted 2021-06-15 cs.LG cs.CL

classification cs.LGcs.CL
keywords transformerpairconnectcompute-efficientalternativeassociatedattentioncomputationallanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Transformer models have demonstrated superior performance in natural language processing. The dot product self-attention in Transformer allows us to model interactions between words. However, this modeling comes with significant computational overhead. In this work, we revisit the memory-compute trade-off associated with Transformer, particularly multi-head attention, and show a memory-heavy but significantly more compute-efficient alternative to Transformer. Our proposal, denoted as PairConnect, a multilayer perceptron (MLP), models the pairwise interaction between words by explicit pairwise word embeddings. As a result, PairConnect substitutes self dot product with a simple embedding lookup. We show mathematically that despite being an MLP, our compute-efficient PairConnect is strictly more expressive than Transformer. Our experiment on language modeling tasks suggests that PairConnect could achieve comparable results with Transformer while reducing the computational cost associated with inference significantly.

Discussion (0). Sign in to comment.

Pith tools