AdaGrid:面向链接预测训练目标的自适应网格搜索
AdaGrid: Adaptive Grid Search for Link Prediction Training Objective
摘要:
有助于机器学习模型成功的最重要因素之一是良好的训练目标。训练目标对模型的性能和泛化能力有重要影响。本文专门针对图神经网络训练目标的链接预测,这在现有的文献中还没有探讨。这里,训练目标包括负采样策略和各种超参数,例如控制如何使用训练边缘的边缘消息比。通常,这些超参数通过完全网格搜索进行微调,这非常耗时且依赖于模型。为了减轻这些限制,我们提出了自适应网格搜索(AdaGrid),它在训练过程中动态调整边缘消息比率。它与模型无关,具有高度可扩展性,具有完全可定制的计算预算。通过大量的实验,我们表明,AdaGrid可以提高性能的模型高达$1.9\%$,同时是9倍的时间效率比一个完整的搜索。总的来说,AdaGrid代表了一种有效的自动化算法,用于设计机器学习训练目标。
英文摘要:
One of the most important factors that contribute to the success of a machine learning model is a good training objective. Training objective crucially influences the model's performance and generalization capabilities. This paper specifically focuses on graph neural network training objective for link prediction, which has not been explored in the existing literature. Here, the training objective includes, among others, a negative sampling strategy, and various hyperparameters, such as edge message ratio which controls how training edges are used. Commonly, these hyperparameters are fine-tuned by complete grid search, which is very time-consuming and model-dependent. To mitigate these limitations, we propose Adaptive Grid Search (AdaGrid), which dynamically adjusts the edge message ratio during training. It is model agnostic and highly scalable with a fully customizable computational budget. Through extensive experiments, we show that AdaGrid can boost the performance of the models up to $1.9\%$ while being nine times more time-efficient than a complete search. Overall, AdaGrid represents an effective automated algorithm for designing machine learning training objectives.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。