首页/论文/2108.10751

arXiv 2108.107512021-08-23cs.LGcs.AIcs.ITcs.NEmath.IT

Understanding the Basis of Graph Convolutional Neural Networks via an Intuitive Matched Filtering Approach

University of Montenegro（黑山大学）；Imperial College London（伦敦帝国理工学院）

Ljubisa Stankovic, Danilo Mandic

备注：: 14 pages, 6 figures, 1 table

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Graph Convolutional Neural Networks (GCNN) are becoming a preferred model for data processing on irregular domains, yet their analysis and principles of operation are rarely examined due to the black box nature of NNs. To this end, we revisit the operation of GCNNs and show that their convolution layers effectively perform matched filtering of input data with the chosen patterns (features). This allows us to provide a unifying account of GCNNs through a matched filter perspective, whereby the nonlinear ReLU and max-pooling layers are also discussed within the matched filtering framework. This is followed by a step-by-step guide on information propagation and learning in GCNNs. It is also shown that standard CNNs and fully connected NNs can be obtained as a special case of GCNNs. A carefully chosen numerical example guides the reader through the various steps of GCNN operation and learning both visually and numerically.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Convolutional Neural Networks Demystified: A Matched Filtering Perspective Based Tutorial

University of Montenegro（黑山大学）；Imperial College London（伦敦帝国理工学院）

Deep Neural Networks (DNN) and especially Convolutional Neural Networks (CNN) are a de-facto standard for the analysis of large volumes of signals and images. Yet, their development and underlying principles have been largely performed in an ad-hoc and black box fashion. To help demystify CNNs, we revisit their operation from first principles and a matched filtering perspective. We establish that the convolution operation within CNNs, their very backbone, represents a matched filter which examines the input signal/image for the presence of pre-defined features. This perspective is shown to be …

2022-03-22cs.AIcs.ITcs.NE

Generalized Approach to Matched Filtering using Neural Networks

Columbia University in the City of New York（纽约市哥伦比亚大学）；University of Florida（佛罗里达大学）

Gravitational wave science is a pioneering field with rapidly evolving data analysis methodology currently assimilating and inventing deep learning techniques. The bulk of the sophisticated flagship searches of the field rely on the time-tested matched filtering principle within their core. In this paper, we make a key observation on the relationship between the emerging deep learning and the traditional techniques: matched filtering is formally equivalent to a particular neural network. This means that a neural network can be constructed analytically to exactly implement matched filtering, an…

2022-02-02astro-ph.HEastro-ph.IMcs.LG

CoverBLIP: scalable iterative matched filtering for MR Fingerprint recovery

University of Edinburgh（爱丁堡大学）；Heriot-Watt University（赫瑞-瓦特大学）

Current proposed solutions for the high dimensionality of the MRF reconstruction problem rely on a linear compression step to reduce the matching computations and boost the efficiency of fast but non-scalable searching schemes such as the KD-trees. However such methodologies often introduce an unfavourable compromise in the estimation accuracy when applied to nonlinear data structures such as the manifold of Bloch responses with possible increased dynamic complexity and growth in data population. To address this shortcoming we propose an inexact iterative reconstruction method, dubbed as the C…

2018-09-06cs.LGq-bio.QM

Signal recognition and background suppression by matched filters and neural networks for Tunka-Rex

Institute of Applied Physics ISU（伊尔库茨克国立大学应用物理研究所）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）；University of Zürich（苏黎世大学）；Vrije Universiteit Brussel（布鲁塞尔自由大学）；Skobeltsyn Institute of Nuclear Physics MSU（莫斯科国立大学斯科别利岑核物理研究所）

The Tunka Radio Extension (Tunka-Rex) is a digital antenna array, which measures the radio emission of the cosmic-ray air-showers in the frequency band of 30-80 MHz. Tunka-Rex is co-located with TAIGA experiment in Siberia and consists of 63 antennas, 57 of them are in a densely instrumented area of about 1 km\textsuperscript{2}. In the present work we discuss the improvements of the signal reconstruction applied for the Tunka-Rex. At the first stage we implemented matched filtering using averaged signals as template. The simulation study has shown that matched filtering allows one to decrease…

2019-06-24astro-ph.IMcs.LGeess.SP

包含高次谐波的引力波模板库新方法：将匹配滤波成本降低一个数量级以上

New approach to template banks of gravitational waves with higher harmonics: Reducing matched-filtering cost by over an order of magnitude

Institute for Advanced Study（高等研究院）；University of California at Santa Barbara（加州大学圣巴巴拉分校）；Tata Institute of Fundamental Research（塔塔基础研究院）；California Institute of Technology（加州理工学院）；Princeton University（普林斯顿大学）；Weizmann Institute of Science（魏茨曼科学研究所）

提出一种分离存储并单独滤波高次谐波模板的新策略，结合后牛顿公式与机器学习建模波形，将引力波搜索的匹配滤波成本降低至纯四极搜索的约3倍，显著提升了搜索效率。

2024-10-17astro-ph.HEastro-ph.IMcs.AI

广泛线性匹配滤波器：复值卷积神经网络可解释性的关键

Widely Linear Matched Filter: A Lynchpin towards the Interpretability of Complex-valued CNNs

Soochow University（苏州大学）；University of Banja Luka（巴尼亚卢卡大学）；Jiaxing Nanhu University（嘉兴南湖学院）；University of Montenegro（黑山大学）；Imperial College London（伦敦帝国学院）

该研究提出通用广泛线性匹配滤波器（WLMF）范式并推导其解与性能，证明其信噪比优于严格线性匹配滤波器，为复值卷积神经网络的可解释性提供了物理意义的支撑。

2024-01-31cs.LG

更多相关论文收起更多论文

Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks

Columbia University in the City of New York（纽约市哥伦比亚大学）；University of Florida（佛罗里达大学）

Gravitational wave astronomy is a vibrant field that leverages both classic and modern data processing techniques for the understanding of the universe. Various approaches have been proposed for improving the efficiency of the detection scheme, with hierarchical matched filtering being an important strategy. Meanwhile, deep learning methods have recently demonstrated both consistency with matched filtering methods and remarkable statistical performance. In this work, we propose Hierarchical Detection Network (HDN), a novel approach to efficient detection that combines ideas from hierarchical m…

2022-07-23astro-ph.IMcs.LGgr-qc

Improved deep learning techniques in gravitational-wave data analysis

Peking University（北京大学）；Kavli Institute for Astronomy and Astrophysics, Peking University（北京大学科维理天文与天体物理研究所）；National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台）；Beijing Normal University（北京师范大学）

In recent years, convolutional neural network (CNN) and other deep learning models have been gradually introduced into the area of gravitational-wave (GW) data processing. Compared with the traditional matched-filtering techniques, CNN has significant advantages in efficiency in GW signal detection tasks. In addition, matched-filtering techniques are based on the template bank of the existing theoretical waveform, which makes it difficult to find GW signals beyond theoretical expectation. In this paper, based on the task of GW detection of binary black holes, we introduce the optimization tech…

2020-12-23astro-ph.HEcs.LGgr-qc

教师的少量步骤作用显著：智能体训练后基于策略的数据增强的成本效益

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training

Stanford University（斯坦福大学）；New York University（纽约大学）

研究针对大语言模型智能体，将基于策略的数据构建视为预算分配问题，通过特定方式形式化设计空间，在多个任务中实验表明少量教师步骤在学习者诱导情境下更具成本效益。

2026-09-01cs.AIcs.LG

理解数据过滤在多模态对比学习中的收益

Understanding the Gain from Data Filtering in Multimodal Contrastive Learning

Paul G. Allen School of Computer Science and Engineering（保罗·G·艾伦计算机科学与工程学院）

本文研究了数据过滤在多模态对比学习中的收益，通过理论分析证明了过滤能有效降低误差，提升模型性能。

2025-12-16cs.LGstat.ML

Collaborative Ensemble Learning: Combining Collaborative and Content-Based Information Filtering via Hierarchical Bayes

Siemens Corporate Technology（西门子企业技术）；Microsoft Research Asia（微软亚洲研究院）

Collaborative filtering (CF) and content-based filtering (CBF) have widely been used in information filtering applications. Both approaches have their strengths and weaknesses which is why researchers have developed hybrid systems. This paper proposes a novel approach to unify CF and CBF in a probabilistic framework, named collaborative ensemble learning. It uses probabilistic SVMs to model each user's profile (as CBF does).At the prediction phase, it combines a society OF users profiles, represented by their respective SVM models, to predict an active users preferences(the CF idea).The combin…

2012-10-19cs.IRcs.LGstat.ML

无模型神经滤波：在非线性系统中与经典滤波器的比较

Model-Free Neural Filtering: A Comparison with Classical Filters in Nonlinear Systems

University of Southern California（南加州大学）

本文比较了无模型神经滤波器与经典滤波器在非线性系统中的性能，发现结构化的状态空间模型在多个场景中表现优异，尤其在无系统模型的情况下表现突出，同时在推理吞吐量上也具有优势。

2026-05-09cs.LG

揭示移除预算混杂：一种用于自适应数据清洗的匹配操作点评估框架

Unmasking Removal-Budget Confounding: A Matched Operating-Point Evaluation Framework for Adaptive Data Cleaning

该研究针对自适应数据清洗中存在的移除预算混杂问题，提出匹配操作点评估框架，经 CIFAR-10、ImageNet-100 实验验证，可消除虚假性能提升，确保结果反映真实损坏区分能力。

2026-08-10cs.LG