PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention. PoM aggregates input tokens into a compact representation through a learned polynomial function, from which each token retrieves contextual information. We prove that PoM satisfies the contextual mapping property, ensuring that transformers equipped with PoM remain universal sequence-to-sequence approximators. We replace standard self-attention with PoM across five diverse domains: text generation, handwritten text recognition, image generation, 3D modeling, and Earth observation. PoM matches the performance of attention-based models while drastically reducing computational cost when working with long sequences. The code is available at https://github.com/davidpicard/pom.
Code (0)
등록된 구현이 없습니다.
Tasks
Handwritten Text RecognitionImage GenerationText GenerationSimilar Papers 제목 키워드 기반
PoM: Efficient Image and Video Generation with the Polynomial Mixer
Diffusion models based on Multi-Head Attention (MHA) have become ubiquitous to generate high quality images and videos. However, encoding an image or a video as a sequence of patches results in costly attention patterns,…
Video GenerationPolynomial Mixing for Efficient Self-supervised Speech Encoders
State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of self-attention in both memory and compu…
Representation LearningSpeech RecognitionHydra: Bidirectional State Space Models Through Generalized Matrix Mixers
A wide array of sequence models are built on a framework modeled after Transformers, comprising alternating sequence mixer and channel mixer layers. This paper studies a unifying matrix mixer view of sequence mixers that…
MambaState Space ModelsPADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Notably, several recent alternative attenti…
2D Object DetectionComputational EfficiencyGPUimage-classification+4ChebMixer: Efficient Graph Representation Learning with MLP Mixer
Graph neural networks have achieved remarkable success in learning graph representations, especially graph Transformer, which has recently shown superior performance on various graph mining tasks. However, graph Transfor…
Graph MiningGraph Representation LearningImage SegmentationMedical Image Segmentation+3