paper-with-me

홈 › Papers

Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference

2019-05-15 · Lukas Galke, Iacopo Vagliano, Ansgar Scherp

Large-scale graph data in real-world applications is often not static but dynamic, i. e., new nodes and edges appear over time. Current graph convolution approaches are promising, especially, when all the graph's nodes and edges are available during training. When unseen nodes and edges are inserted after training, it is not yet evaluated whether up-training or re-training from scratch is preferable. We construct an experimental setup, in which we insert previously unseen nodes and edges after training and conduct a limited amount of inference epochs. In this setup, we compare adapting pretrained graph neural networks against retraining from scratch. Our results show that pretrained models yield high accuracy scores on the unseen nodes and that pretraining is preferable over retraining from scratch. Our experiments represent a first step to evaluate and develop truly online variants of graph neural networks.

📄 PDF Abstract BibTeX arXiv:1905.06018

Code (1)

lgalke/gnn-pretraining-evaluation 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Self-Supervised Pretraining Improves Performance and Inference Efficiency in Multiple Lung Ultrasound Interpretation Tasks

2023-09-05 · Blake VanBerlo, Brian Li, Jesse Hoey, Alexander Wong

In this study, we investigated whether self-supervised pretraining could produce a neural network feature extractor applicable to multiple classification tasks in B-mode lung ultrasound analysis. When fine-tuning on thre…

Pretrain-Test Task Alignment Governs Generalization in In-Context Learning

2025-09-30 · Mary I. Letey, Jacob A. Zavatone-Veth, Yue M. Lu, Cengiz Pehlevan arxiv

In-context learning (ICL) is a central capability of Transformer models, but the structures in data that enable its emergence and govern its robustness remain poorly understood. In this work, we study how the structure o…

TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining

2021-10-26 · Viet-Anh Nguyen, Anh H. T. Nguyen, Andy W. H. Khong

We introduce a block-online variant of the temporal feature-wise linear modulation (TFiLM) model to achieve bandwidth extension. The proposed architecture simplifies the UNet backbone of the TFiLM to reduce inference tim…

Audio Super-ResolutionBandwidth ExtensionSensitivity

Online Inference for Mixture Model of Streaming Graph Signals with Non-White Excitation

2022-07-28 · Yiran He, Hoi-To Wai

This paper considers a joint multi-graph inference and clustering problem for simultaneous inference of node centrality and association of graph signals with their graphs. We study a mixture model of filtered low pass gr…

Graph Learning

A Systematic Study of Model Extraction Attacks on Graph Foundation Models

2025-11-14 · Haoyan Xu, Ruizhi Qian, Jiate Li, Yushun Dong 외 arxiv

Graph machine learning has advanced rapidly in tasks such as link prediction, anomaly detection, and node classification. As models scale up, pretrained graph models have become valuable intellectual assets because they …

Node ClassificationAnomaly DetectionModel extractionFraud Detection