BriefGPT.xyz
Nov, 2024
重新考虑图自编码器在链接预测中的表现
Reconsidering the Performance of GAE in Link Prediction
HTML
PDF
Weishuo Ma, Yanbo Wang, Xiyuan Wang, Muhan Zhang
TL;DR
本研究针对链接预测任务中存在的旧基准模型导致的新模型优越性被高估的问题，系统地探索了图自编码器（GAE）的潜力。通过精细调节超参数及采用正交嵌入和线性传播技巧，研究发现经过优化的GAE在性能上可与更复杂模型相匹配，同时提供更高的计算效率。
Abstract
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 However, outdated baseline models may lead to an overestimation of the benefi
→