Pith. sign in

REVIEW 10 cited by

Random Feature 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 2103.02143 v2 pith:YPESEIV7 submitted 2021-03-03 cs.CL

Random Feature Attention

classification cs.CL
keywords attentionlongtransformercomparedefficiencyfastfeaturefunction
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not scale efficiently to long sequences due to its quadratic time and space complexity in the sequence length. We propose RFA, a linear time and space attention that uses random feature methods to approximate the softmax function, and explore its application in transformers. RFA can be used as a drop-in replacement for conventional softmax attention and offers a straightforward way of learning with recency bias through an optional gating mechanism. Experiments on language modeling and machine translation demonstrate that RFA achieves similar or better performance compared to strong transformer baselines. In the machine translation experiment, RFA decodes twice as fast as a vanilla transformer. Compared to existing efficient transformer variants, RFA is competitive in terms of both accuracy and efficiency on three long text classification datasets. Our analysis shows that RFA's efficiency gains are especially notable on long sequences, suggesting that RFA will be particularly useful in tasks that require working with large inputs, fast decoding speed, or low memory footprints.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

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

  1. Blurry Window Attention

    cs.LG 2026-05 unverdicted novelty 6.0

    Blurry Window Attention stores a frequency window and reconstructs blurry KV history via Dirichlet kernel interpolation, achieving 8x better state efficiency than sliding window attention on the MQAR synthetic task.

  2. Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders

    cs.CV 2026-05 unverdicted novelty 6.0

    C-GSPN scales 2D spatial propagation to foundation vision encoders via a fast CUDA kernel, compressed blocks, and two-stage distillation, matching ViT performance with 15% fewer parameters and 4x block speedup at 2K r...

  3. Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations

    cs.LG 2026-05 unverdicted novelty 6.0

    Oryx hybridizes attention and linear recurrent mixers along the sequence axis with high parameter sharing, outperforming single-mixer baselines on language modeling and retrieval at up to 1.4B scale under mixed training.

  4. Elastic Attention Cores for Scalable Vision Transformers

    cs.CV 2026-05 unverdicted novelty 6.0

    VECA learns effective visual representations using core-periphery attention where patches interact exclusively via a resolution-invariant set of learned core embeddings, achieving linear O(N) complexity while maintain...

  5. Attention to Mamba: A Recipe for Cross-Architecture Distillation

    cs.CL 2026-04 unverdicted novelty 6.0

    A two-stage distillation recipe converts a Pythia-1B Transformer into a Mamba model that preserves performance with perplexity 14.11 versus the teacher's 13.86.

  6. M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling

    cs.LG 2026-03 unverdicted novelty 6.0

    M²RNN achieves perfect state tracking at unseen lengths and outperforms Gated DeltaNet hybrids by 0.4-0.5 perplexity on 7B models with 3x smaller recurrent states.

  7. Higher-order Linear Attention

    cs.LG 2025-10 unverdicted novelty 6.0

    Higher-order Linear Attention realizes second-order and higher interactions in linear-time causal attention via constant-size state and associative scans.

  8. Gated Linear Attention Transformers with Hardware-Efficient Training

    cs.LG 2023-12 unverdicted novelty 6.0

    Gated linear attention Transformers achieve competitive language modeling results with linear-time inference, superior length generalization, and higher training throughput than Mamba.

  9. General-Purpose Nonlinear Function Approximation via Linear Integrated Photonics

    cs.ET 2026-06 unverdicted novelty 5.0

    Optical random Fourier feature mapping enables approximation of tenth-order polynomials, special functions, neural activations, and high-dimensional softmax in linear silicon photonic hardware.

  10. Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging

    cs.LG 2026-05 unverdicted novelty 5.0

    Randomly initialized Transformers act as adaptive sequence smoothers for sleep staging via a Random Attention Prior Kernel, with gains mainly from inductive bias rather than training.