论文标题
GraphTTA：图神经网络上的测试时间适应
GraphTTA: Test Time Adaptation on Graph Neural Networks
论文作者
论文摘要
最近，由于其处理现实世界中的分配变化问题，测试时间适应（TTA）引起了越来越多的关注。与用于图像数据的卷积神经网络（CNN）开发的内容不同，对于图形神经网络（GNN），TTA的探索较少。仍然缺乏针对具有不规则结构的图的有效算法。在本文中，我们提出了一种新颖的测试时间适应策略，称为图形伪群体对比度（GAPGC），用于图神经网络TTA，以更好地适应过分分布（OOD）测试数据。具体而言，GAPGC在TTA期间采用对比度学习变体作为一项自制任务，配备了对抗性可学习的增强器和组伪阳性样本，以增强自我监督任务与主要任务之间的相关性，从而促进了主要任务的绩效。此外，我们提供了理论上的证据，表明GAPGC可以从信息理论的角度提取主要任务的最小信息。关于分子支架OOD数据集的广泛实验表明，所提出的方法在GNN上实现了最先进的表现。
Recently, test time adaptation (TTA) has attracted increasing attention due to its power of handling the distribution shift issue in the real world. Unlike what has been developed for convolutional neural networks (CNNs) for image data, TTA is less explored for Graph Neural Networks (GNNs). There is still a lack of efficient algorithms tailored for graphs with irregular structures. In this paper, we present a novel test time adaptation strategy named Graph Adversarial Pseudo Group Contrast (GAPGC), for graph neural networks TTA, to better adapt to the Out Of Distribution (OOD) test data. Specifically, GAPGC employs a contrastive learning variant as a self-supervised task during TTA, equipped with Adversarial Learnable Augmenter and Group Pseudo-Positive Samples to enhance the relevance between the self-supervised task and the main task, boosting the performance of the main task. Furthermore, we provide theoretical evidence that GAPGC can extract minimal sufficient information for the main task from information theory perspective. Extensive experiments on molecular scaffold OOD dataset demonstrated that the proposed approach achieves state-of-the-art performance on GNNs.
