校准与改进图对比学习
Calibrating and Improving Graph Contrastive Learning
AI总结：
针对无监督图对比学习中部分对比对与下游任务真相相悖、降低其损失会损害下游性能的问题，提出即插即用正则化方法Contrast-Reg，经理论和实验验证可有效提升不同配置下GNN模型的泛化性与下游任务性能。
摘要：
图对比学习算法已在节点分类、链路预测和图聚类等各类应用中展现出显著成效。然而，在无监督图对比学习中，部分对比对可能与下游任务的真实情况相悖，因此降低这些对比对的损失会对下游任务性能产生不利影响。为评估这些对比对在下游任务中的预测值与真实值之间的差异，我们将期望校准误差（ECE）适配应用于图对比学习。基于对ECE的分析，我们提出了一种新型正则化方法Contrast-Reg，以确保降低对比损失能够提升下游任务的性能。作为一种即插即用的正则化项，Contrast-Reg可有效提升现有图对比学习算法的性能。我们提供了理论与实证结果，证明Contrast-Reg在增强图神经网络（GNN）模型的泛化性、提升采用不同相似度定义和编码器骨干的图对比算法在各类下游任务中的性能方面均具备有效性。
英文摘要：
Graph contrastive learning algorithms have demonstrated remarkable success in various applications such as node classification, link prediction, and graph clustering. However, in unsupervised graph contrastive learning, some contrastive pairs may contradict the truths in downstream tasks and thus the decrease of losses on these pairs undesirably harms the performance in the downstream tasks. To assess the discrepancy between the prediction and the ground-truth in the downstream tasks for these contrastive pairs, we adapt the expected calibration error (ECE) to graph contrastive learning. The analysis of ECE motivates us to propose a novel regularization method, Contrast-Reg, to ensure that decreasing the contrastive loss leads to better performance in the downstream tasks. As a plug-in regularizer, Contrast-Reg effectively improves the performance of existing graph contrastive learning algorithms. We provide both theoretical and empirical results to demonstrate the effectiveness of Contrast-Reg in enhancing the generalizability of the Graph Neural Network(GNN) model and improving the performance of graph contrastive algorithms with different similarity definitions and encoder backbones across various downstream tasks.
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。
