Simplicial Attention Networks

• URL: http://arxiv.org/abs/2203.07485v1
• Date: Mon, 14 Mar 2022 20:47:31 GMT
• Title: Simplicial Attention Networks
• Authors: L. Giusti, C. Battiloro, P. Di Lorenzo, S. Sardellitti, S. Barbarossa
• Abstract summary: We introduce a proper self-attention mechanism able to process data components at different layers. We learn how to weight both upper and lower neighborhoods of the given topological domain in a totally task-oriented fashion. The proposed approach compares favorably with other methods when applied to different (inductive and transductive) tasks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The aim of this work is to introduce simplicial attention networks (SANs), i.e., novel neural architectures that operate on data defined on simplicial complexes leveraging masked self-attentional layers. Hinging on formal arguments from topological signal processing, we introduce a proper self-attention mechanism able to process data components at different layers (e.g., nodes, edges, triangles, and so on), while learning how to weight both upper and lower neighborhoods of the given topological domain in a totally task-oriented fashion. The proposed SANs generalize most of the current architectures available for processing data defined on simplicial complexes. The proposed approach compares favorably with other methods when applied to different (inductive and transductive) tasks such as trajectory prediction and missing data imputations in citation complexes.

Related papers

• SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes [61.110517195874074]
  We present a scheme to directly generate manifold, polygonal meshes of complex connectivity as the output of a neural network. Our key innovation is to define a continuous latent connectivity space at each mesh, which implies the discrete mesh. In applications, this approach not only yields high-quality outputs from generative models, but also enables directly learning challenging geometry processing tasks such as mesh repair.
  arXiv  Detail & Related papers  (2024-09-30T17:59:03Z)
• Defining Neural Network Architecture through Polytope Structures of Dataset [53.512432492636236]
  This paper defines upper and lower bounds for neural network widths, which are informed by the polytope structure of the dataset in question. We develop an algorithm to investigate a converse situation where the polytope structure of a dataset can be inferred from its corresponding trained neural networks. It is established that popular datasets such as MNIST, Fashion-MNIST, and CIFAR10 can be efficiently encapsulated using no more than two polytopes with a small number of faces.
  arXiv  Detail & Related papers  (2024-02-04T08:57:42Z)
• On Characterizing the Evolution of Embedding Space of Neural Networks using Algebraic Topology [9.537910170141467]
  We study how the topology of feature embedding space changes as it passes through the layers of a well-trained deep neural network (DNN) through Betti numbers. We demonstrate that as depth increases, a topologically complicated dataset is transformed into a simple one, resulting in Betti numbers attaining their lowest possible value.
  arXiv  Detail & Related papers  (2023-11-08T10:45:12Z)
• Generalized Simplicial Attention Neural Networks [22.171364354867723]
  We introduce Generalized Simplicial Attention Neural Networks (GSANs) GSANs process data living on simplicial complexes using masked self-attentional layers. These schemes learn how to combine data associated with neighbor simplices of consecutive order in a task-oriented fashion.
  arXiv  Detail & Related papers  (2023-09-05T11:29:25Z)
• Pooling Strategies for Simplicial Convolutional Networks [18.80397868603073]
  The goal of this paper is to introduce pooling strategies for simplicial convolutional neural networks. Inspired by graph pooling methods, we introduce a general formulation for a simplicial pooling layer. The general layer is then customized to design four different pooling strategies.
  arXiv  Detail & Related papers  (2022-10-11T14:45:51Z)
• Inducing Gaussian Process Networks [80.40892394020797]
  We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points. The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains. We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-21T05:27:09Z)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)
• Layer-stacked Attention for Heterogeneous Network Embedding [0.0]
  Layer-stacked ATTention Embedding (LATTE) is an architecture that automatically decomposes higher-order meta relations at each layer. LATTE offers a more interpretable aggregation scheme for nodes of different types at different neighborhood ranges. In both transductive and inductive node classification tasks, LATTE can achieve state-of-the-art performance compared to existing approaches.
  arXiv  Detail & Related papers  (2020-09-17T05:13:41Z)
• Decontextualized learning for interpretable hierarchical representations of visual patterns [0.0]
  We present an algorithm and training paradigm designed specifically to address this: decontextualized hierarchical representation learning (DHRL) DHRL address the limitations of small datasets and encourages a disentangled set of hierarchically organized features. In addition to providing a tractable path for analyzing complex hierarchal patterns using variation inference, this approach is generative and can be directly combined with empirical and theoretical approaches.
  arXiv  Detail & Related papers  (2020-08-31T14:47:55Z)
• GCN for HIN via Implicit Utilization of Attention and Meta-paths [104.24467864133942]
  Heterogeneous information network (HIN) embedding aims to map the structure and semantic information in a HIN to distributed representations. We propose a novel neural network method via implicitly utilizing attention and meta-paths. We first use the multi-layer graph convolutional network (GCN) framework, which performs a discriminative aggregation at each layer. We then give an effective relaxation and improvement via introducing a new propagation operation which can be separated from aggregation.
  arXiv  Detail & Related papers  (2020-07-06T11:09:40Z)
• Seismic horizon detection with neural networks [62.997667081978825]
  This paper is an open-sourced research of applying binary segmentation approach to the task of horizon detection on multiple real seismic cubes with a focus on inter-cube generalization of the predictive model. The main contribution of this paper is an open-sourced research of applying binary segmentation approach to the task of horizon detection on multiple real seismic cubes with a focus on inter-cube generalization of the predictive model.
  arXiv  Detail & Related papers  (2020-01-10T11:30:50Z)

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.