Source Free Unsupervised Graph Domain Adaptation
arXiv:2112.00955 · doi:10.1145/3616855.3635802
Abstract
Graph Neural Networks (GNNs) have achieved great success on a variety of tasks with graph-structural data, among which node classification is an essential one. Unsupervised Graph Domain Adaptation (UGDA) shows its practical value of reducing the labeling cost for node classification. It leverages knowledge from a labeled graph (i.e., source domain) to tackle the same task on another unlabeled graph (i.e., target domain). Most existing UGDA methods heavily rely on the labeled graph in the source domain. They utilize labels from the source domain as the supervision signal and are jointly trained on both the source graph and the target graph. However, in some real-world scenarios, the source graph is inaccessible because of privacy issues. Therefore, we propose a novel scenario named Source Free Unsupervised Graph Domain Adaptation (SFUGDA). In this scenario, the only information we can leverage from the source domain is the well-trained source model, without any exposure to the source graph and its labels. As a result, existing UGDA methods are not feasible anymore. To address the non-trivial adaptation challenges in this practical scenario, we propose a model-agnostic algorithm called SOGA for domain adaptation to fully exploit the discriminative ability of the source model while preserving the consistency of structural proximity on the target graph. We prove the effectiveness of the proposed algorithm both theoretically and empirically. The experimental results on four cross-domain tasks show consistent improvements in the Macro-F1 score and Macro-AUC.
arXiv comment12 pages, 6 figures
References in corpus (21)
- Adam: A Method for Stochastic Optimization
- DeepWalk: Online Learning of Social Representations
- Unsupervised Domain Adaptation by Backpropagation
- Deep Domain Confusion: Maximizing for Domain Invariance
- struc2vec: Learning Node Representations from Structural Identity
- GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
- Model Adaptation: Unsupervised Domain Adaptation without Source Data
- Asymmetric Tri-training for Unsupervised Domain Adaptation
- Deep Graph Contrastive Representation Learning
- Learning Structural Node Embeddings Via Diffusion Wavelets
- Peer-to-peer Federated Learning on Graphs
- Network Together: Node Classification via Cross network Deep Network Embedding
- Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
- GPT-GNN: Generative Pre-Training of Graph Neural Networks
- Federated Graph Classification over Non-IID Graphs
- Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
- Learning on Graphs with Out-of-Distribution Nodes
- Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
- Empowering Graph Representation Learning with Test-Time Graph Transformation
- Revisiting Link Prediction: A Data Perspective
- Company Competition Graph