paper-with-me

홈 › Papers

Training-free Graph Neural Networks and the Power of Labels as Features

2024-04-30 · Ryoma Sato

We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably enhances the expressive power of graph neural networks. We design TFGNNs based on this analysis. In the experiments, we confirm that TFGNNs outperform existing GNNs in the training-free setting and converge with much fewer training iterations than traditional GNNs.

📄 PDF Abstract BibTeX arXiv:2404.19288

Code (1)

joisino/laf 공식 구현 pytorch

Tasks

Node Classification

Similar Papers 제목 키워드 기반

FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding

2025-06-16 · Chenlu Zhan, Gaoang Wang, Hongwei Wang

Semantic querying in complex 3D scenes through free-form language presents a significant challenge. Existing 3D scene understanding methods use large-scale training data and CLIP to align text queries with 3D semantic fe…

FormGraph GenerationRelational ReasoningScene Understanding

Why Propagate Alone? Parallel Use of Labels and Features on Graphs

2021-10-14 · ICLR 2022 4 · Yangkun Wang, Jiarui Jin, Weinan Zhang, Yongyi Yang 외

Graph neural networks (GNNs) and label propagation represent two interrelated modeling strategies designed to exploit graph structure in tasks such as node property prediction. The former is typically based on stacked me…

Node Property PredictionProperty Prediction

Theoretical Analysis of the Optimal Free Responses of Graph-Based SFA for the Design of Training Graphs

2015-09-28 · Alberto N. Escalante-B., Laurenz Wiskott

Slow feature analysis (SFA) is an unsupervised learning algorithm that extracts slowly varying features from a time series. Graph-based SFA (GSFA) is a supervised extension that can solve regression problems if followed …

regressionTime SeriesTime Series Analysis

Graph Filtration Kernels

2021-10-22 · Till Hendrik Schulz, Pascal Welke, Stefan Wrobel

The majority of popular graph kernels is based on the concept of Haussler's $\mathcal{R}$-convolution kernel and defines graph similarities in terms of mutual substructures. In this work, we enrich these similarity measu…

MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs

2019-01-21 · Alistair E. W. Johnson, Tom J. Pollard, Nathaniel R. Greenbaum, Matthew P. Lungren 외

Chest radiography is an extremely powerful imaging modality, allowing for a detailed inspection of a patient's thorax, but requiring specialized training for proper interpretation. With the advent of high performance gen…