Domain-adaptive Message Passing Graph Neural Network
arXiv:2308.16470 · doi:10.1016/j.neunet.2023.04.038
Abstract
Cross-network node classification (CNNC), which aims to classify nodes in a label-deficient target network by transferring the knowledge from a source network with abundant labels, draws increasing attention recently. To address CNNC, we propose a domain-adaptive message passing graph neural network (DM-GNN), which integrates graph neural network (GNN) with conditional adversarial domain adaptation. DM-GNN is capable of learning informative representations for node classification that are also transferrable across networks. Firstly, a GNN encoder is constructed by dual feature extractors to separate ego-embedding learning from neighbor-embedding learning so as to jointly capture commonality and discrimination between connected nodes. Secondly, a label propagation node classifier is proposed to refine each node's label prediction by combining its own prediction and its neighbors' prediction. In addition, a label-aware propagation scheme is devised for the labeled source network to promote intra-class propagation while avoiding inter-class propagation, thus yielding label-discriminative source embeddings. Thirdly, conditional adversarial domain adaptation is performed to take the neighborhood-refined class-label information into account during adversarial domain adaptation, so that the class-conditional distributions across networks can be better matched. Comparisons with eleven state-of-the-art methods demonstrate the effectiveness of the proposed DM-GNN.
arXiv commentThis version rectifies the numerical inaccuracies of Table 3 and 4 in the printed version (https://doi.org/10.1016/j.neunet.2023.04.038). See our corrigendum at https://doi.org/10.1016/j.neunet.2023.09.026
References in corpus (18)
- Conditional Generative Adversarial Nets
- DeepWalk: Online Learning of Social Representations
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Towards Deeper Graph Neural Networks
- Node Classification in Social Networks
- Scaling Graph Neural Networks with Approximate PageRank
- Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification
- Revisiting Semi-Supervised Learning with Graph Embeddings
- REGAL: Representation Learning-based Graph Alignment
- Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
- Language-aware Domain Generalization Network for Cross-Scene Hyperspectral Image Classification
- Deep Network Embedding for Graph Representation Learning in Signed Networks
- Network Together: Node Classification via Cross network Deep Network Embedding
- Transfer Learning across Networks for Collective Classification
- Progressive Graph Learning for Open-Set Domain Adaptation
- Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks