Pith. sign in

REVIEW 1 cited by

Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT

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 2203.09055 v1 pith:IOV3LKNY submitted 2022-03-17 cs.CL

classification cs.CL
keywords self-attentionbertcoarse-granularitytokensaccuracycomputationalcomputingcost
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Transformer-based pre-trained models, such as BERT, have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, deploying these models can be prohibitively costly, as the standard self-attention mechanism of the Transformer suffers from quadratic computational cost in the input sequence length. To confront this, we propose FCA, a fine- and coarse-granularity hybrid self-attention that reduces the computation cost through progressively shortening the computational sequence length in self-attention. Specifically, FCA conducts an attention-based scoring strategy to determine the informativeness of tokens at each layer. Then, the informative tokens serve as the fine-granularity computing units in self-attention and the uninformative tokens are replaced with one or several clusters as the coarse-granularity computing units in self-attention. Experiments on GLUE and RACE datasets show that BERT with FCA achieves 2x reduction in FLOPs over original BERT with <1% loss in accuracy. We show that FCA offers a significantly better trade-off between accuracy and FLOPs compared to prior methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TreeKV: Smooth Key-Value Cache Compression with Tree Structures

    cs.CL 2025-01 conditional novelty 5.0 of 10

    TreeKV uses a cyclic pair-wise eviction tree with averaged attention scores to compress LLM KV caches, reporting SOTA perplexity on PG19/OpenWebText2 and best LongBench averages.

Pith tools