CKConv: Continuous Kernel Convolution For Sequential Data

• URL: http://arxiv.org/abs/2102.02611v1
• Date: Thu, 4 Feb 2021 13:51:19 GMT
• Title: CKConv: Continuous Kernel Convolution For Sequential Data
• Authors: David W. Romero, Anna Kuzina, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
• Abstract summary: Continuous Kernel Convolutional Networks (CKCNNs) are designed to handle non-uniformly sampled datasets and irregularly-sampled data. CKCNNs match or perform better than neural ODEs designed for these purposes in a much faster and simpler manner.
• Score: 23.228639801282966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially. Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori. In this work, we show that all these problems can be solved by formulating convolutional kernels in CNNs as continuous functions. The resulting Continuous Kernel Convolution (CKConv) allows us to model arbitrarily long sequences in a parallel manner, within a single operation, and without relying on any form of recurrence. We show that Continuous Kernel Convolutional Networks (CKCNNs) obtain state-of-the-art results in multiple datasets, e.g., permuted MNIST, and, thanks to their continuous nature, are able to handle non-uniformly sampled datasets and irregularly-sampled data natively. CKCNNs match or perform better than neural ODEs designed for these purposes in a much faster and simpler manner.

Related papers

• Scalable Graph Compressed Convolutions [68.85227170390864]
  We propose a differentiable method that applies permutations to calibrate input graphs for Euclidean convolution. Based on the graph calibration, we propose the Compressed Convolution Network (CoCN) for hierarchical graph representation learning.
  arXiv  Detail & Related papers  (2024-07-26T03:14:13Z)
• Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series [26.77596449192451]
  Irregularly sampled time series are ubiquitous in several application domains, leading to sparse, not fully-observed and non-aligned observations. Standard sequential neural networks (RNNs) and convolutional neural networks (CNNs) consider regular spacing between observation times, posing significant challenges to irregular time series modeling. We parameterize convolutional layers by employing time-explicitly irregular kernels.
  arXiv  Detail & Related papers  (2023-08-06T21:10:30Z)
• 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)
• Continuous-time convolutions model of event sequences [46.3471121117337]
  Event sequences are non-uniform and sparse, making traditional models unsuitable. We propose COTIC, a method based on an efficient convolution neural network designed to handle the non-uniform occurrence of events over time. COTIC outperforms existing models in predicting the next event time and type, achieving an average rank of 1.5 compared to 3.714 for the nearest competitor.
  arXiv  Detail & Related papers  (2023-02-13T10:34:51Z)
• Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK [86.45209429863858]
  We study training one-hidden-layer ReLU networks in the neural tangent kernel (NTK) regime. We show that the neural networks possess a different limiting kernel which we call textitbias-generalized NTK We also study various properties of the neural networks with this new kernel.
  arXiv  Detail & Related papers  (2023-01-01T02:11:39Z)
• Towards a General Purpose CNN for Long Range Dependencies in $\mathrm{N}$D [49.57261544331683]
  We propose a single CNN architecture equipped with continuous convolutional kernels for tasks on arbitrary resolution, dimensionality and length without structural changes. We show the generality of our approach by applying the same CCNN to a wide set of tasks on sequential (1$mathrmD$) and visual data (2$mathrmD$) Our CCNN performs competitively and often outperforms the current state-of-the-art across all tasks considered.
  arXiv  Detail & Related papers  (2022-06-07T15:48:02Z)
• Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks [10.014879130837912]
  We propose a symmetric multi-scale architecture called Circular Dilated Convolutional Neural Network (CDIL-CNN) Our model gives classification logits in all positions, and we can apply a simple ensemble learning to achieve a better decision.
  arXiv  Detail & Related papers  (2022-01-06T16:58:59Z)
• Scaling Neural Tangent Kernels via Sketching and Random Features [53.57615759435126]
  Recent works report that NTK regression can outperform finitely-wide neural networks trained on small-scale datasets. We design a near input-sparsity time approximation algorithm for NTK, by sketching the expansions of arc-cosine kernels. We show that a linear regressor trained on our CNTK features matches the accuracy of exact CNTK on CIFAR-10 dataset while achieving 150x speedup.
  arXiv  Detail & Related papers  (2021-06-15T04:44:52Z)
• Deep Parametric Continuous Convolutional Neural Networks [92.87547731907176]
  Parametric Continuous Convolution is a new learnable operator that operates over non-grid structured data. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes.
  arXiv  Detail & Related papers  (2021-01-17T18:28:23Z)
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution [57.635467829558664]
  We introduce a structural regularization across convolutional kernels in a CNN. We show that CNNs now maintain performance with dramatic reduction in parameters and computations.
  arXiv  Detail & Related papers  (2020-09-04T20:41:47Z)

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.