paper-with-me

홈 › Papers

DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters

2019-10-24 · NeurIPS 2019 12 · Asiri Wijesinghe, Qing Wang

We propose a novel spectral convolutional neural network (CNN) model on graph structured data, namely Distributed Feedback-Looped Networks (DFNets). This model is incorporated with a robust class of spectral graph filters, called feedback-looped filters, to provide better localization on vertices, while still attaining fast convergence and linear memory requirements. Theoretically, feedback-looped filters can guarantee convergence w.r.t. a specified error bound, and be applied universally to any graph without knowing its structure. Furthermore, the propagation rule of this model can diversify features from the preceding layers to produce strong gradient flows. We have evaluated our model using two benchmark tasks: semi-supervised document classification on citation networks and semi-supervised entity classification on a knowledge graph. The experimental results show that our model considerably outperforms the state-of-the-art methods in both benchmark tasks over all datasets.

📄 PDF Abstract BibTeX arXiv:1910.10866

Code (1)

wokas36/DFNets 공식 구현 tf

Tasks

Document ClassificationGeneral ClassificationNode Classification

Similar Papers 제목 키워드 기반

Hypergraphs as Weighted Directed Self-Looped Graphs: Spectral Properties, Clustering, Cheeger Inequality

2024-10-23 · Zihao Li, Dongqi Fu, Hengyu Liu, Jingrui He

Hypergraphs naturally arise when studying group relations and have been widely used in the field of machine learning. There has not been a unified formulation of hypergraphs, yet the recently proposed edge-dependent vert…

Clustering

Parcae: Scaling Laws For Stable Looped Language Models

2026-04-14 · Hayden Prairie, Zachary Novack, Taylor Berg-Kirkpatrick, Daniel Y. Fu arxiv

Traditional fixed-depth architectures scale quality by increasing training FLOPs, typically through increased parameterization, at the expense of a higher memory footprint, or data. A potential alternative is looped arch…

A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs

2022-10-20 · Lequan Lin, Junbin Gao

Spectral Graph Convolutional Networks (spectral GCNNs), a powerful tool for analyzing and processing graph data, typically apply frequency filtering via Fourier transform to obtain representations with selective informat…

DenoisingLink PredictionNode Classification

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

2016-06-30 · NeurIPS 2016 12 · Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst

In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as socia…

Node ClassificationSkeleton Based Action Recognition

Stability and Generalization in Looped Transformers

2026-04-16 · Asher Labovich arxiv

Looped transformers promise test-time compute scaling by spending more iterations on harder problems, but it remains unclear which architectural choices let them extrapolate to harder problems at test time rather than me…