Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling

• URL: http://arxiv.org/abs/2408.09453v1
• Date: Sun, 18 Aug 2024 12:20:03 GMT
• Title: Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
• Authors: Harry Jake Cunningham, Giorgio Giannone, Mingtian Zhang, Marc Peter Deisenroth,
• Abstract summary: We present a novel approach to parameterizing global convolutional kernels for long-sequence modelling. Our experiments demonstrate state-of-the-art performance on the Long Range Arena, Sequential CIFAR, and Speech Commands tasks. We also report improved performance on ImageNet classification by replacing 2D convolutions with 1D $textttMRConv$ layers.
• Score: 13.627888191693712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is challenging, and kernel parameterizations must be able to learn long-range dependencies without overfitting. This work introduces reparameterized multi-resolution convolutions ($\texttt{MRConv}$), a novel approach to parameterizing global convolutional kernels for long-sequence modelling. By leveraging multi-resolution convolutions, incorporating structural reparameterization and introducing learnable kernel decay, $\texttt{MRConv}$ learns expressive long-range kernels that perform well across various data modalities. Our experiments demonstrate state-of-the-art performance on the Long Range Arena, Sequential CIFAR, and Speech Commands tasks among convolution models and linear-time transformers. Moreover, we report improved performance on ImageNet classification by replacing 2D convolutions with 1D $\texttt{MRConv}$ layers.

Related papers

• PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting [82.03373838627606]
  Self-attention mechanism in Transformer architecture requires positional embeddings to encode temporal order in time series prediction. We argue that this reliance on positional embeddings restricts the Transformer's ability to effectively represent temporal sequences. We present a model integrating PRE with a standard Transformer encoder, demonstrating state-of-the-art performance on various real-world datasets.
  arXiv  Detail & Related papers  (2024-08-20T01:56:07Z)
• LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory [63.41820940103348]
  Self-attention mechanism's computational cost limits its practicality for long sequences. We propose a new method called LongVQ to compress the global abstraction as a length-fixed codebook. LongVQ effectively maintains dynamic global and local patterns, which helps to complement the lack of long-range dependency issues.
  arXiv  Detail & Related papers  (2024-04-17T08:26:34Z)
• Sample Complexity Characterization for Linear Contextual MDPs [67.79455646673762]
  Contextual decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with different MDPs indexed by a context variable. CMDPs serve as an important framework to model many real-world applications with time-varying environments. We study CMDPs under two linear function approximation models: Model I with context-varying representations and common linear weights for all contexts; and Model II with common representations for all contexts and context-varying linear weights.
  arXiv  Detail & Related papers  (2024-02-05T03:25:04Z)
• Sequence Modeling with Multiresolution Convolutional Memory [27.218134279968062]
  We build a new building block for sequence modeling called a MultiresLayer. The key component of our model is the multiresolution convolution, capturing multiscale trends in the input sequence. Our model yields state-of-the-art performance on a number of sequence classification and autoregressive density estimation tasks.
  arXiv  Detail & Related papers  (2023-05-02T17:50:54Z)
• SMPConv: Self-moving Point Representations for Continuous Convolution [4.652175470883851]
  This paper presents an alternative approach to building a continuous convolution without neural networks. We present self-moving point representations where weight parameters freely move, and schemes are used to implement continuous functions. Due to its lightweight structure, we are first to demonstrate the effectiveness of continuous convolution in a large-scale setting.
  arXiv  Detail & Related papers  (2023-04-05T09:36:30Z)
• Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution [46.32359056424278]
  Large convolutional kernels have become popular in designing convolutional neural networks. The increase in kernel size also leads to a quadratic growth in the number of parameters, resulting in heavy computation and memory requirements. We propose a neighborhood attention (NA) module that upgrades the standard convolution with a self-attention mechanism. Building upon the NA module, we propose a lightweight single image super-resolution (SISR) network named TCSR.
  arXiv  Detail & Related papers  (2023-03-25T01:32:18Z)
• DO-Conv: Depthwise Over-parameterized Convolutional Layer [66.46704754669169]
  We propose to augment a convolutional layer with an additional depthwise convolution, where each input channel is convolved with a different 2D kernel. We show with extensive experiments that the mere replacement of conventional convolutional layers with DO-Conv layers boosts the performance of CNNs.
  arXiv  Detail & Related papers  (2020-06-22T06:57:10Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)
• Supervised Learning for Non-Sequential Data: A Canonical Polyadic Decomposition Approach [85.12934750565971]
  Efficient modelling of feature interactions underpins supervised learning for non-sequential tasks. To alleviate this issue, it has been proposed to implicitly represent the model parameters as a tensor. For enhanced expressiveness, we generalize the framework to allow feature mapping to arbitrarily high-dimensional feature vectors.
  arXiv  Detail & Related papers  (2020-01-27T22:38:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.