paper-with-me

Papers

FNetAR: Mixing Tokens with Autoregressive Fourier Transforms

2021-07-22 · Tim Lou, Michael Park, Mohammad Ramezanali, Vincent Tang

In this note we examine the autoregressive generalization of the FNet algorithm, in which self-attention layers from the standard Transformer architecture are substituted with a trivial sparse-uniformsampling procedure based on Fourier transforms. Using the Wikitext-103 benchmark, we demonstratethat FNetAR retains state-of-the-art performance (25.8 ppl) on the task of causal language modelingcompared to a Transformer-XL baseline (24.2 ppl) with only half the number self-attention layers,thus providing further evidence for the superfluity of deep neural networks with heavily compoundedattention mechanisms. The autoregressive Fourier transform could likely be used for parameterreduction on most Transformer-based time-series prediction models.

📄 PDF Abstract BibTeX arXiv:2107.10932

Code (1)

MindCode-4/code-3/tree/main/fnet mindspore

Tasks

Language ModellingTime SeriesTime Series AnalysisTime Series Prediction

Methods 이 논문이 사용한 방법론

Attention 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Adaptive Input Representations Adaptive Input Embeddings extend the adaptive softmax to input word representations. The factorization assigns more…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

New Approaches to Long Document Summarization: Fourier Transform Based Attention in a Transformer Model

2021-11-25 · Andrew Kiruluta, Andreas Lemos, Eric Lundy

In this work, we extensively redesign the newly introduced method of token mixing using Fourier Transforms (FNET) to replace the computationally expensive self-attention mechanism in a full transformer implementation on …

Abstractive Text SummarizationDecoderDocument Summarization

FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation

2025-03-04 · Andrew Kiruluta, Eric Lundy, Andreas Lemos

We present FourierNAT, a novel non-autoregressive Transformer (NAT) architecture that employs Fourier-based mixing in the decoder to generate output sequences in parallel. While traditional NAT approaches often face chal…

DecoderMachine TranslationText Generation

FNet: Mixing Tokens with Fourier Transforms

2021-05-09 · NAACL 2022 7 · James Lee-Thorp, Joshua Ainslie, Ilya Eckstein, Santiago Ontanon

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…

Linguistic AcceptabilityMachine TranslationNatural Language InferenceParaphrase Identification+4

A Quasi-Newton algorithm on the orthogonal manifold for NMF with transform learning

2018-11-06 · Pierre Ablin, Dylan Fagot, Herwig Wendt, Alexandre Gramfort 외

Nonnegative matrix factorization (NMF) is a popular method for audio spectral unmixing. While NMF is traditionally applied to off-the-shelf time-frequency representations based on the short-time Fourier or Cosine transfo…

Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector

2023-12-18 · An Lao, Qi Zhang, Chongyang Shi, Longbing Cao 외

Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media. Existing multimodal rumor detection has focused on mixing tokens among spatial and sequential locat…

Contrastive Learning