Pith. sign in

REVIEW 11 cited by

FNet: Mixing Tokens with Fourier Transforms

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 2105.03824 v4 pith:ISLS4SUC submitted 2021-05-09 cs.CL cs.LG

FNet: Mixing Tokens with Fourier Transforms

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

We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. These linear mixers, along with standard nonlinearities in feed-forward layers, prove competent at modeling semantic relationships in several text classification tasks. Most surprisingly, we find that replacing the self-attention sublayer in a Transformer encoder with a standard, unparameterized Fourier Transform achieves 92-97% of the accuracy of BERT counterparts on the GLUE benchmark, but trains 80% faster on GPUs and 70% faster on TPUs at standard 512 input lengths. At longer input lengths, our FNet model is significantly faster: when compared to the "efficient" Transformers on the Long Range Arena benchmark, FNet matches the accuracy of the most accurate models, while outpacing the fastest models across all sequence lengths on GPUs (and across relatively shorter lengths on TPUs). Finally, FNet has a light memory footprint and is particularly efficient at smaller model sizes; for a fixed speed and accuracy budget, small FNet models outperform Transformer counterparts.

discussion (0)

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

Forward citations

Cited by 11 Pith papers

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

  1. Beyond Sinusoids: A Morlet Wavelet Framework for Transformer Positional Encoding

    cs.LG 2026-05 unverdicted novelty 7.0

    MoPE replaces fixed sinusoidal or rotary positional encodings with per-dimension learned Morlet wavelets that recover prior methods as limits and add a Gaussian locality kernel, yielding a 0.119 gain on TinyShakespear...

  2. Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

    cs.LG 2026-04 unverdicted novelty 7.0

    NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.

  3. Latent Fourier Transform

    cs.SD 2026-04 unverdicted novelty 7.0

    LatentFT uses latent-space Fourier transforms and frequency masking in diffusion autoencoders to enable timescale-specific manipulation of musical structure in generative models.

  4. Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

    cs.LG 2024-05 unverdicted novelty 7.0

    Transformers and SSMs are unified through structured state space duality, producing a 2-8X faster Mamba-2 model that remains competitive with Transformers.

  5. FourierQK: Spectral Preprocessing of Query-Key Projections Improves Transformer Attention

    cs.LG 2026-07 conditional novelty 6.0

    FFT-based spectral preprocessing of Q/K projections reduces character-level TinyShakespeare validation loss by up to 79% over standard dot-product attention, with gains attributed to phase-coherent global sequence mixing.

  6. Chiaroscuro Attention: Spending Compute in the Dark

    cs.CL 2026-06 unverdicted novelty 6.0

    CHIAR-Former routes tokens via spectral entropy to DCT mixing or attention, yielding 35-40% FLOP savings at 400M parameters with modest perplexity increase on WikiText-103.

  7. 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.

  8. HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet

    cs.CV 2026-04 unverdicted novelty 6.0

    HAMSA achieves 85.7% ImageNet-1K top-1 accuracy as a spectral-domain SSM with 2.2x faster inference and lower memory than transformers or scanning-based SSMs.

  9. Positional Encoding via Token-Aware Phase Attention

    cs.CL 2025-09 unverdicted novelty 6.0

    TAPA adds a learnable phase function to attention to preserve long-range token interactions, enabling direct continual pretraining, length extrapolation, lower perplexity, and stronger retrieval than RoPE-style methods.

  10. Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models

    cs.CV 2025-08 unverdicted novelty 6.0

    Fourier Compressor uses FFT to remove frequency-domain redundancy from visual tokens in VLMs, retaining over 96% accuracy with up to 83.8% FLOP reduction.

  11. AudioKV: KV Cache Eviction in Efficient Large Audio Language Models

    cs.SD 2026-04 unverdicted novelty 5.0

    AudioKV prioritizes audio-critical attention heads identified via ASR analysis and applies spectral score smoothing to evict KV cache tokens, achieving high compression with minimal accuracy loss in LALMs.