Edge Dithering for Robust Adaptive Graph Convolutional Networks

2019-10-21 · Vassilis N. Ioannidis, Georgios B. Giannakis

Graph convolutional networks (GCNs) are vulnerable to perturbations of the graph structure that are either random, or, adversarially designed. The perturbed links modify the graph neighborhoods, which critically affects the performance of GCNs in semi-supervised learning (SSL) tasks. Aiming at robustifying GCNs conditioned on the perturbed graph, the present paper generates multiple auxiliary graphs, each having its binary 0-1 edge weights flip values with probabilities designed to enhance robustness. The resultant edge-dithered auxiliary graphs are leveraged by an adaptive (A)GCN that performs SSL. Robustness is enabled through learnable graph-combining weights along with suitable regularizers. Relative to GCN, the novel AGCN achieves markedly improved performance in tests with noisy inputs, graph perturbations, and state-of-the-art adversarial attacks. Further experiments with protein interaction networks showcase the competitive performance of AGCN for SSL over multiple graphs.

📄 PDF Abstract BibTeX arXiv:1910.09590

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

AGCN AGCN is a novel spectral graph convolution network that feed on original data of diverse graph structures. Image credit: [Adaptive Graph Convolutional Neural…

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Adaptive Learning-Based Detection for One-Bit Quantized Massive MIMO Systems

2022-11-13 · Yunseong Cho, Jinseok Choi, Brian L. Evans

We propose an adaptive learning-based framework for uplink massive multiple-input multiple-output (MIMO) systems with one-bit analog-to-digital converters. Learning-based detection does not need to estimate channels, whi…

Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering

2026-05-21 · Yury Belousov, Brian Pulfer, Vitaliy Kinakh, Slava Voloshynovskiy arxiv

Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial attack. We study multi-level Floyd-Steinberg error-diffusion dithering as…

Visual Question Answering Adversarial Robustness Adversarial Attack Depth Estimation

Learning-Based One-Bit Maximum Likelihood Detection for Massive MIMO Systems: Dithering-Aided Adaptive Approach

2023-04-16 · Yunseong Cho, Jinseok Choi, Brian L. Evans

In this paper, we propose a learning-based detection framework for uplink massive multiple-input and multiple-output (MIMO) systems with one-bit analog-to-digital converters. The learning-based detection only requires co…

Active Restoration of Lost Audio Signals Using Machine Learning and Latent Information

2021-11-21 · Zohra Adila Cheddad, Abbas Cheddad

Digital audio signal reconstruction of a lost or corrupt segment using deep learning algorithms has been explored intensively in recent years. Nevertheless, prior traditional methods with linear interpolation, phase codi…

Audio inpainting Deep Learning Image Reconstruction

Optimizing Audio Compression Through Entropy-Controlled Dithering

2025-01-04 · Ellison Murray, Morriel Kasher, Predrag Spasojevic

This paper explores entropy-controlled dithering techniques in audio compression, examining the application of standard and modified TPDFs, combined with noise shaping and entropy-controlled parameters, across various au…

Audio Compression Rhythm