链接预测任务中的隐式度偏差
Implicit degree bias in the link prediction task
AI总结:
本研究揭示链接预测任务中边采样对高度数节点的隐式偏差,提出度校正基准以提供更合理评估,并证明其能更有效训练图模型。
摘要:
链接预测——即区分真实隐藏边与随机未连接节点对的任务——是图机器学习中的典型任务之一。尽管该任务被广泛接受为通用基准和表示学习的下游任务,但链接预测基准本身的有效性却很少受到质疑。在此,我们表明链接预测任务中常见的边采样过程对高度数节点存在隐式偏差,并产生高度偏斜的评估,这种评估偏向于过度依赖节点度的方法,以至于仅基于节点度的“空”链接预测方法也能产生近乎最优的性能。我们提出了一种度校正的链接预测任务,该任务提供了更合理的评估,与推荐任务中的性能更一致。最后,我们证明度校正基准可以通过减少对节点度的过拟合并促进图中有相关结构的学习,更有效地训练图机器学习模型。
英文摘要:
Link prediction -- a task of distinguishing actual hidden edges from random unconnected node pairs -- is one of the quintessential tasks in graph machine learning. Despite being widely accepted as a universal benchmark and a downstream task for representation learning, the validity of the link prediction benchmark itself has been rarely questioned. Here, we show that the common edge sampling procedure in the link prediction task has an implicit bias toward high-degree nodes and produces a highly skewed evaluation that favors methods overly dependent on node degree, to the extent that a ``null'' link prediction method based solely on node degree can yield nearly optimal performance. We propose a degree-corrected link prediction task that offers a more reasonable assessment that aligns better with the performance in the recommendation task. Finally, we demonstrate that the degree-corrected benchmark can more effectively train graph machine-learning models by reducing overfitting to node degrees and facilitating the learning of relevant structures in graphs.
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。