Related papers: Low-Rank Projections of GCNs Laplacian

Low-Rank Projections of GCNs Laplacian

URL: http://arxiv.org/abs/2106.07360v1
Date: Fri, 4 Jun 2021 09:54:26 GMT
Title: Low-Rank Projections of GCNs Laplacian
Authors: Nathan Grinsztajn (Scool), Philippe Preux (Scool), Edouard Oyallon (MLIA)
Abstract summary: We study the behavior of standard models for community detection under spectral manipulations. We empirically show that most of the necessary and used information for nodes classification is contained in the low-frequency domain.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In this work, we study the behavior of standard models for community detection under spectral manipulations. Through various ablation experiments, we evaluate the impact of bandpass filtering on the performance of a GCN: we empirically show that most of the necessary and used information for nodes classification is contained in the low-frequency domain, and thus contrary to images, high frequencies are less crucial to community detection. In particular, it is sometimes possible to obtain accuracies at a state-of-the-art level with simple classifiers that rely only on a few low frequencies.

Related papers

Frequency-regularized Neural Representation Method for Sparse-view Tomographic Reconstruction [8.45338755060592]
We introduce the Regularized Neural Attenuation/Activity Field (Freq-NAF) for self-supervised sparse-view tomographic reconstruction. Freq-NAF mitigates overfitting by frequency regularization, directly controlling the visible frequency bands in the neural network input.
arXiv Detail & Related papers (2024-09-22T11:19:38Z)
Towards a Novel Perspective on Adversarial Examples Driven by Frequency [7.846634028066389]
We propose a black-box adversarial attack algorithm based on combining different frequency bands. Experiments conducted on multiple datasets and models demonstrate that combining low-frequency bands and high-frequency components of low-frequency bands can significantly enhance attack efficiency.
arXiv Detail & Related papers (2024-04-16T00:58:46Z)
Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning [81.98675881423131]
This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
arXiv Detail & Related papers (2024-03-12T01:28:00Z)
FS-BAND: A Frequency-Sensitive Banding Detector [55.59101150019851]
Banding artifact, as known as staircase-like contour, is a common quality annoyance that happens in compression, transmission, etc. We propose a no-reference banding detection model to capture and evaluate banding artifacts, called the Frequency-Sensitive BANding Detector (FS-BAND) Experimental results show that the proposed FS-BAND method outperforms state-of-the-art image quality assessment (IQA) approaches with higher accuracy in banding classification task.
arXiv Detail & Related papers (2023-11-30T03:20:42Z)
High Dynamic Range Image Quality Assessment Based on Frequency Disparity [78.36555631446448]
An image quality assessment (IQA) algorithm based on frequency disparity for high dynamic range ( HDR) images is proposed. The proposed LGFM can provide a higher consistency with the subjective perception compared with the state-of-the-art HDR IQA methods.
arXiv Detail & Related papers (2022-09-06T08:22:13Z)
How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations? [27.865987936475797]
Recent studies have shown that data augmentation can result in model over-relying on features in the low-frequency domain. We propose Jacobian frequency regularization for models' Jacobians to have a larger ratio of low-frequency components. Our approach elucidates a more direct connection between the frequency bias and robustness of deep learning models.
arXiv Detail & Related papers (2022-05-09T20:09:31Z)
Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification [74.84221280249876]
An efficient analysis of large amounts of chest radiographs can aid physicians and radiologists. We propose a novel Discrete Wavelet Transform (DWT)-based method for the efficient identification and encoding of visual information.
arXiv Detail & Related papers (2022-05-08T15:29:54Z)
Adaptive Frequency Learning in Two-branch Face Forgery Detection [66.91715092251258]
We propose Adaptively learn Frequency information in the two-branch Detection framework, dubbed AFD. We liberate our network from the fixed frequency transforms, and achieve better performance with our data- and task-dependent transform layers.
arXiv Detail & Related papers (2022-03-27T14:25:52Z)
Unsupervised Image Denoising with Frequency Domain Knowledge [2.834895018689047]
Supervised learning-based methods yield robust denoising results, yet they are inherently limited by the need for large-scale datasets. In this study we propose a frequency-sensitive unsupervised denoising method. Results using natural and synthetic datasets indicate that our unsupervised learning method augmented with frequency information achieves state-of-the-art denoising performance.
arXiv Detail & Related papers (2021-11-29T07:41:32Z)
Explicit Regularisation in Gaussian Noise Injections [64.11680298737963]
We study the regularisation induced in neural networks by Gaussian noise injections (GNIs) We derive the explicit regulariser of GNIs, obtained by marginalising out the injected noise. We show analytically and empirically that such regularisation produces calibrated classifiers with large classification margins.
arXiv Detail & Related papers (2020-07-14T21:29:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.