Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels
This work addresses a key challenge in graph-based semi-supervised learning for applications like social networks or recommendation systems, though it is incremental as it builds on existing self-training methods.
The paper tackles the problem of distribution shift between labeled and unlabeled nodes in few-shot node classification for Graph Neural Networks (GNNs) by proposing a Distribution-Consistent Graph Self-Training (DC-GST) framework, which consistently outperforms state-of-the-art baselines on four benchmark datasets.
Few-shot node classification poses a significant challenge for Graph Neural Networks (GNNs) due to insufficient supervision and potential distribution shifts between labeled and unlabeled nodes. Self-training has emerged as a widely popular framework to leverage the abundance of unlabeled data, which expands the training set by assigning pseudo-labels to selected unlabeled nodes. Efforts have been made to develop various selection strategies based on confidence, information gain, etc. However, none of these methods takes into account the distribution shift between the training and testing node sets. The pseudo-labeling step may amplify this shift and even introduce new ones, hindering the effectiveness of self-training. Therefore, in this work, we explore the potential of explicitly bridging the distribution shift between the expanded training set and test set during self-training. To this end, we propose a novel Distribution-Consistent Graph Self-Training (DC-GST) framework to identify pseudo-labeled nodes that are both informative and capable of redeeming the distribution discrepancy and formulate it as a differentiable optimization task. A distribution-shift-aware edge predictor is further adopted to augment the graph and increase the model's generalizability in assigning pseudo labels. We evaluate our proposed method on four publicly available benchmark datasets and extensive experiments demonstrate that our framework consistently outperforms state-of-the-art baselines.