Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes

Test-time adaptation aims to adapt a well-trained model using test data only, without accessing training data. It is a crucial topic in machine learning, enabling a wide range of applications in the real world, especially when it comes to data privacy. While existing works on test-time adaptation primarily focus on Euclidean data, research on non-Euclidean graph data remains scarce. Prevalent graph neural network methods could encounter serious performance degradation in the face of test-time domain shifts. In this work, we propose a novel method named Adaptive Subgraph-based Selection and Regularized Prototype Supervision (ASSESS) for reliable test-time adaptation on graphs. Specifically, to achieve flexible selection of reliable test graphs, ASSESS adopts an adaptive selection strategy based on fine-grained individual-level subgraph mutual information. Moreover, to utilize the information from both training and test graphs, ASSESS constructs semantic prototypes from the well-trained model as prior knowledge from the unknown training graphs and optimizes the posterior given the unlabeled test graphs. We also provide a theoretical analysis of the proposed algorithm. Extensive experiments verify the effectiveness of ASSESS against various baselines.

Artificial intelligence can be used to predict the properties of graph-structured data, like proteins or small molecules. However, when AI faces proteins or molecules significantly different from what it saw before, it may fail to predict their properties correctly. We design a machine learning algorithm that helps AI perform better in this scenario. This enhances the AI's ability to handle more cases in graph-structured data, like proteins or small molecules.