paper-with-me

Papers

Reconsidering the Performance of GAE in Link Prediction

2024-11-06 · Weishuo Ma, Yanbo Wang, Xiyuan Wang, Muhan Zhang

Various graph neural networks (GNNs) with advanced training techniques and model designs have been proposed for link prediction tasks. However, outdated baseline models may lead to an overestimation of the benefits provided by these novel approaches. To address this, we systematically investigate the potential of Graph Autoencoders (GAE) by meticulously tuning hyperparameters and utilizing the trick of orthogonal embedding and linear propagation. Our findings reveal that a well-optimized GAE can match the performance of more complex models while offering greater computational efficiency.

📄 PDF Abstract BibTeX arXiv:2411.03845

Code (2)

graphpku/refined-gae 공식 구현 pytorch
GraphPKU/Refined-GAE pytorch

Tasks

Computational EfficiencyLink PredictionPrediction

Similar Papers 제목 키워드 기반

Is Machine Learning Unsafe and Irresponsible in Social Sciences? Paradoxes and Reconsidering from Recidivism Prediction Tasks

2023-11-11 · Jianhong Liu, Dianshi Li

The paper addresses some fundamental and hotly debated issues for high-stakes event predictions underpinning the computational approach to social sciences. We question several prevalent views against machine learning and…

Biber Redux: Reconsidering Dimensions of Variation in American English

2014-08-01 · COLING 2014 8 · Rebecca J. Passonneau, Nancy Ide, Songqiao Su, Jesse Stuart
Domain AdaptationInformation RetrievalLanguage ModellingMachine Translation+3

When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction

2022-06-04 · Vinith M. Suriyakumar, Marzyeh Ghassemi, Berk Ustun

Machine learning models are often personalized with categorical attributes that are protected, sensitive, self-reported, or costly to acquire. In this work, we show models that are personalized with group attributes can …

Reconsidering Explicit Longitudinal Mammography Alignment for Enhanced Breast Cancer Risk Prediction

2025-06-24 · Solveig Thrun, Stine Hansen, Zijun Sun, Nele Blum 외

Regular mammography screening is essential for early breast cancer detection. Deep learning-based risk prediction methods have sparked interest to adjust screening intervals for high-risk groups. While early methods focu…

Breast Cancer DetectionPrediction

Path-SGD: Path-Normalized Optimization in Deep Neural Networks

2015-06-08 · NeurIPS 2015 12 · Behnam Neyshabur, Ruslan Salakhutdinov, Nathan Srebro

We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect th…