paper-with-me

홈 › Papers

DCT: Dynamic Compressive Transformer for Modeling Unbounded Sequence

2021-10-10 · Kai-Po Chang, Wei-Yun Ma

In this paper, we propose Dynamic Compressive Transformer (DCT), a transformer-based framework for modeling the unbounded sequence. In contrast to the previous baselines which append every sentence representation to memory, conditionally selecting and appending them is a more reasonable solution to deal with unlimited long sequences. Our model uses a policy that determines whether the sequence should be kept in memory with a compressed state or discarded during the training process. With the benefits of retaining semantically meaningful sentence information in the memory system, our experiment results on Enwik8 benchmark show that DCT outperforms the previous state-of-the-art (SOTA) model.

📄 PDF Abstract BibTeX arXiv:2110.04821

Code (0)

등록된 구현이 없습니다.

Tasks

Sentence

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Compressed Memory Compressed Memory is a secondary FIFO memory component proposed as part of the Compressive Transformer model. The…
Adam 설명 없음

Similar Papers 제목 키워드 기반

CSformer: Bridging Convolution and Transformer for Compressive Sensing

2021-12-31 · Dongjie Ye, Zhangkai Ni, Hanli Wang, Jian Zhang 외

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in model…

Compressive SensingInductive BiasRepresentation Learning

MICA: Multivariate Infini Compressive Attention for Time Series Forecasting

2026-04-07 · Willa Potosnak, Nina Żukowska, Michał Wiliński, Dan Howarth 외 arxiv

Multivariate forecasting with Transformers faces a core scalability challenge: modeling cross-channel dependencies via attention compounds attention's quadratic sequence complexity with quadratic channel scaling, making …

Time Series Forecasting

Compressive Transformers for Long-Range Sequence Modelling

2019-11-13 · ICLR 2020 1 · Jack W. Rae, Anna Potapenko, Siddhant M. Jayakumar, Timothy P. Lillicrap

We present the Compressive Transformer, an attentive sequence model which compresses past memories for long-range sequence learning. We find the Compressive Transformer obtains state-of-the-art language modelling results…

Language Modelling

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

2024-04-10 · Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention …

Book summarizationLanguage ModelingLanguage ModellingRetrieval

Compressive Acquisition of Dynamic Scenes

2012-01-23 · Aswin C. Sankaranarayanan, Pavan K Turaga, Rama Chellappa, Richard G. Baraniuk

Compressive sensing (CS) is a new approach for the acquisition and recovery of sparse signals and images that enables sampling rates significantly below the classical Nyquist rate. Despite significant progress in the the…

Compressive Sensing