Topological Neural Networks over the Air
- URL: http://arxiv.org/abs/2502.10070v1
- Date: Fri, 14 Feb 2025 10:45:36 GMT
- Title: Topological Neural Networks over the Air
- Authors: Simone Fiorellino, Claudio Battiloro, Paolo Di Lorenzo,
- Abstract summary: Topological neural networks (TNNs) are information processing architectures that model representations from data lying over topological spaces.
This paper proposes a novel TNN design, operating on regular cell complexes, that performs over-the-air computation, incorporating the wireless communication model into its architecture.
- Score: 13.291627429657416
- License:
- Abstract: Topological neural networks (TNNs) are information processing architectures that model representations from data lying over topological spaces (e.g., simplicial or cell complexes) and allow for decentralized implementation through localized communications over different neighborhoods. Existing TNN architectures have not yet been considered in realistic communication scenarios, where channel effects typically introduce disturbances such as fading and noise. This paper aims to propose a novel TNN design, operating on regular cell complexes, that performs over-the-air computation, incorporating the wireless communication model into its architecture. Specifically, during training and inference, the proposed method considers channel impairments such as fading and noise in the topological convolutional filtering operation, which takes place over different signal orders and neighborhoods. Numerical results illustrate the architecture's robustness to channel impairments during testing and the superior performance with respect to existing architectures, which are either communication-agnostic or graph-based.
Related papers
- Model-based learning for multi-antenna multi-frequency location-to-channel mapping [6.067275317776295]
Implicit Neural Representation literature showed that classical neural architecture are biased towards learning low-frequency content.
This paper leverages the model-based machine learning paradigm to derive a problem-specific neural architecture from a propagation channel model.
arXiv Detail & Related papers (2024-06-17T13:09:25Z) - TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture.
To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer.
In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
arXiv Detail & Related papers (2024-04-15T06:01:48Z) - Neural Network with Local Converging Input (NNLCI) for Supersonic Flow
Problems with Unstructured Grids [0.9152133607343995]
We develop a neural network with local converging input (NNLCI) for high-fidelity prediction using unstructured data.
As a validation case, the NNLCI method is applied to study inviscid supersonic flows in channels with bumps.
arXiv Detail & Related papers (2023-10-23T19:03:37Z) - Graph-based Multi-ODE Neural Networks for Spatio-Temporal Traffic
Forecasting [8.832864937330722]
Long-range traffic forecasting remains a challenging task due to the intricate and extensive-temporal correlations observed in traffic networks.
In this paper, we propose a architecture called Graph-based Multi-ODE Neural Networks (GRAM-ODE) which is designed with multiple connective ODE-GNN modules to learn better representations.
Our extensive set of experiments conducted on six real-world datasets demonstrate the superior performance of GRAM-ODE compared with state-of-the-art baselines.
arXiv Detail & Related papers (2023-05-30T02:10:42Z) - Graph Neural Networks over the Air for Decentralized Tasks in Wireless Networks [6.007238205454907]
This paper studies the impact of channel impairments on the performance of graph neural networks over the air (AirGNNs)
AirGNNs modify graph convolutional operations that shift graph signals over random communication graphs to take into account channel fading and noise.
Experiments on decentralized source localization and multi-robot flocking show superior performance of AirGNNs over wireless communication channels.
arXiv Detail & Related papers (2023-02-16T17:40:23Z) - Interference Cancellation GAN Framework for Dynamic Channels [74.22393885274728]
We introduce an online training framework that can adapt to any changes in the channel.
Our framework significantly outperforms recent neural network models on highly dynamic channels.
arXiv Detail & Related papers (2022-08-17T02:01:18Z) - Deep Architecture Connectivity Matters for Its Convergence: A
Fine-Grained Analysis [94.64007376939735]
We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training.
We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
arXiv Detail & Related papers (2022-05-11T17:43:54Z) - Self-Learning for Received Signal Strength Map Reconstruction with
Neural Architecture Search [63.39818029362661]
We present a model based on Neural Architecture Search (NAS) and self-learning for received signal strength ( RSS) map reconstruction.
The approach first finds an optimal NN architecture and simultaneously train the deduced model over some ground-truth measurements of a given ( RSS) map.
Experimental results show that signal predictions of this second model outperforms non-learning based state-of-the-art techniques and NN models with no architecture search.
arXiv Detail & Related papers (2021-05-17T12:19:22Z) - On the benefits of robust models in modulation recognition [53.391095789289736]
Deep Neural Networks (DNNs) using convolutional layers are state-of-the-art in many tasks in communications.
In other domains, like image classification, DNNs have been shown to be vulnerable to adversarial perturbations.
We propose a novel framework to test the robustness of current state-of-the-art models.
arXiv Detail & Related papers (2021-03-27T19:58:06Z) - Multi-Tones' Phase Coding (MTPC) of Interaural Time Difference by
Spiking Neural Network [68.43026108936029]
We propose a pure spiking neural network (SNN) based computational model for precise sound localization in the noisy real-world environment.
We implement this algorithm in a real-time robotic system with a microphone array.
The experiment results show a mean error azimuth of 13 degrees, which surpasses the accuracy of the other biologically plausible neuromorphic approach for sound source localization.
arXiv Detail & Related papers (2020-07-07T08:22:56Z)
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.