paper-with-me

Papers

Sparse Diffusion-Convolutional Neural Networks

2017-10-26 · James Atwood, Siddharth Pal, Don Towsley, Ananthram Swami

The predictive power and overall computational efficiency of Diffusion-convolutional neural networks make them an attractive choice for node classification tasks. However, a naive dense-tensor-based implementation of DCNNs leads to $\mathcal{O}(N^2)$ memory complexity which is prohibitive for large graphs. In this paper, we introduce a simple method for thresholding input graphs that provably reduces memory requirements of DCNNs to O(N) (i.e. linear in the number of nodes in the input) without significantly affecting predictive performance.

📄 PDF Abstract BibTeX arXiv:1710.09813

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyGeneral ClassificationNode Classification

Similar Papers 제목 키워드 기반

Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

2022-11-03 · Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon 외

During image editing, existing deep generative models tend to re-synthesize the entire output from scratch, including the unedited regions. This leads to a significant waste of computation, especially for minor editing o…

GPU

Graph Neural Diffusion Networks for Semi-supervised Learning

2022-01-24 · Wei Ye, Zexi Huang, Yunqi Hong, Ambuj Singh

Graph Convolutional Networks (GCN) is a pioneering model for graph-based semi-supervised learning. However, GCN does not perform well on sparsely-labeled graphs. Its two-layer version cannot effectively propagate the lab…

Graph Neural Network

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

2025-05-20 · Zhihao LI, YuFei Wang, Heliang Zheng, Yihao Luo 외

High-fidelity 3D object synthesis remains significantly more challenging than 2D image generation due to the unstructured nature of mesh data and the cubic complexity of dense volumetric grids. Existing two-stage pipelin…

3D Generation3D ReconstructionImage Generation

Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Winds

2025-10-03 · Xiaolong Ma, Xu Dong, Ashley Tarrant, Lei Yang 외 arxiv

High-quality observations of hub-height winds are valuable but sparse in space and time. Simulations are widely available on regular grids but are generally biased and too coarse to inform wind-farm siting or to assess e…

Diffusion-based Generative Prior for Low-Complexity MIMO Channel Estimation

2024-03-06 · Benedikt Fesl, Michael Baur, Florian Strasser, Michael Joham 외

This work proposes a novel channel estimator based on diffusion models (DMs), one of the currently top-rated generative models. Contrary to related works utilizing generative priors, a lightweight convolutional neural ne…