Singular Value Representation: A New Graph Perspective On Neural Networks

• URL: http://arxiv.org/abs/2302.08183v1
• Date: Thu, 16 Feb 2023 10:10:31 GMT
• Title: Singular Value Representation: A New Graph Perspective On Neural Networks
• Authors: Dan Meller and Nicolas Berkouk
• Abstract summary: We introduce the Singular Value Representation (SVR), a new method to represent the internal state of neural networks. We derive a precise statistical framework to discriminate meaningful connections between spectral neurons for fully connected and convolutional layers.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We introduce the Singular Value Representation (SVR), a new method to represent the internal state of neural networks using SVD factorization of the weights. This construction yields a new weighted graph connecting what we call spectral neurons, that correspond to specific activation patterns of classical neurons. We derive a precise statistical framework to discriminate meaningful connections between spectral neurons for fully connected and convolutional layers. To demonstrate the usefulness of our approach for machine learning research, we highlight two discoveries we made using the SVR. First, we highlight the emergence of a dominant connection in VGG networks that spans multiple deep layers. Second, we witness, without relying on any input data, that batch normalization can induce significant connections between near-kernels of deep layers, leading to a remarkable spontaneous sparsification phenomenon.

Related papers

• Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks [5.851101657703105]
  We take a first step towards theoretically characterizing the conditioning of the Gauss-Newton (GN) matrix in neural networks. We establish tight bounds on the condition number of the GN in deep linear networks of arbitrary depth and width. We expand the analysis to further architectural components, such as residual connections and convolutional layers.
  arXiv  Detail & Related papers  (2024-11-04T14:56:48Z)
• Decorrelating neurons using persistence [29.25969187808722]
  We present two regularisation terms computed from the weights of a minimum spanning tree of a clique. We demonstrate that naive minimisation of all correlations between neurons obtains lower accuracies than our regularisation terms. We include a proof of differentiability of our regularisers, thus developing the first effective topological persistence-based regularisation terms.
  arXiv  Detail & Related papers  (2023-08-09T11:09:14Z)
• Addressing caveats of neural persistence with deep graph persistence [54.424983583720675]
  We find that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence. We propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers. This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues.
  arXiv  Detail & Related papers  (2023-07-20T13:34:11Z)
• Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective [53.999128831324576]
  Graph neural networks (GNNs) have pioneered advancements in graph representation learning. This study investigates the role of graph convolution within the context of feature learning theory.
  arXiv  Detail & Related papers  (2023-06-24T10:21:11Z)
• DualHGNN: A Dual Hypergraph Neural Network for Semi-Supervised Node Classification based on Multi-View Learning and Density Awareness [3.698434507617248]
  Graph-based semi-supervised node classification has been shown to become a state-of-the-art approach in many applications with high research value and significance. This paper proposes the Dual Hypergraph Neural Network (DualHGNN), a new dual connection model integrating both hypergraph structure learning and hypergraph representation learning simultaneously in a unified architecture.
  arXiv  Detail & Related papers  (2023-06-07T07:40:04Z)
• Spiking neural network for nonlinear regression [68.8204255655161]
  Spiking neural networks carry the potential for a massive reduction in memory and energy consumption. They introduce temporal and neuronal sparsity, which can be exploited by next-generation neuromorphic hardware. A framework for regression using spiking neural networks is proposed.
  arXiv  Detail & Related papers  (2022-10-06T13:04:45Z)
• Visual Attention Emerges from Recurrent Sparse Reconstruction [82.78753751860603]
  We present a new attention formulation built on two prominent features of the human visual attention mechanism: recurrency and sparsity. We show that self-attention is a special case of VARS with a single-step optimization and no sparsity constraint. VARS can be readily used as a replacement for self-attention in popular vision transformers, consistently improving their robustness across various benchmarks.
  arXiv  Detail & Related papers  (2022-04-23T00:35:02Z)
• Improving Neural Predictivity in the Visual Cortex with Gated Recurrent Connections [0.0]
  We aim to shift the focus on architectures that take into account lateral recurrent connections, a ubiquitous feature of the ventral visual stream, to devise adaptive receptive fields. In order to increase the robustness of our approach and the biological fidelity of the activations, we employ specific data augmentation techniques.
  arXiv  Detail & Related papers  (2022-03-22T17:27:22Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Geometry Perspective Of Estimating Learning Capability Of Neural Networks [0.0]
  The paper considers a broad class of neural networks with generalized architecture performing simple least square regression with gradient descent (SGD) The relationship between the generalization capability with the stability of the neural network has also been discussed. By correlating the principles of high-energy physics with the learning theory of neural networks, the paper establishes a variant of the Complexity-Action conjecture from an artificial neural network perspective.
  arXiv  Detail & Related papers  (2020-11-03T12:03:19Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

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.