Distribution shift mitigation at test time with performance guarantees

by   Rui Ding, et al.

Due to inappropriate sample selection and limited training data, a distribution shift often exists between the training and test sets. This shift can adversely affect the test performance of Graph Neural Networks (GNNs). Existing approaches mitigate this issue by either enhancing the robustness of GNNs to distribution shift or reducing the shift itself. However, both approaches necessitate retraining the model, which becomes unfeasible when the model structure and parameters are inaccessible. To address this challenge, we propose FR-GNN, a general framework for GNNs to conduct feature reconstruction. FRGNN constructs a mapping relationship between the output and input of a well-trained GNN to obtain class representative embeddings and then uses these embeddings to reconstruct the features of labeled nodes. These reconstructed features are then incorporated into the message passing mechanism of GNNs to influence the predictions of unlabeled nodes at test time. Notably, the reconstructed node features can be directly utilized for testing the well-trained model, effectively reducing the distribution shift and leading to improved test performance. This remarkable achievement is attained without any modifications to the model structure or parameters. We provide theoretical guarantees for the effectiveness of our framework. Furthermore, we conduct comprehensive experiments on various public datasets. The experimental results demonstrate the superior performance of FRGNN in comparison to mainstream methods.


page 1

page 2

page 3

page 4


SpotTarget: Rethinking the Effect of Target Edges for Link Prediction in Graph Neural Networks

Graph Neural Networks (GNNs) have demonstrated promising outcomes across...

Dual GNNs: Graph Neural Network Learning with Limited Supervision

Graph Neural Networks (GNNs) require a relatively large number of labele...

Empowering Graph Representation Learning with Test-Time Graph Transformation

As powerful tools for representation learning on graphs, graph neural ne...

Explaining and Adapting Graph Conditional Shift

Graph Neural Networks (GNNs) have shown remarkable performance on graph-...

DropMessage: Unifying Random Dropping for Graph Neural Networks

Graph Neural Networks (GNNs) are powerful tools for graph representation...

Stable Prediction on Graphs with Agnostic Distribution Shift

Graph is a flexible and effective tool to represent complex structures i...

Please sign up or login with your details

Forgot password? Click here to reset