Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
This work addresses scalability issues in GNNs for researchers and practitioners dealing with large graph data, offering incremental improvements over existing decoupling and self-training techniques.
The paper tackles the challenge of scaling Graph Neural Networks (GNNs) to large graphs by proposing SAGN, which adaptively gathers neighborhood information, and SLE, a self-training framework that enhances semi-supervised learning. Experiments show SAGN achieves better or comparable results to existing methods, with SLE further improving performance.
It is hard to directly implement Graph Neural Networks (GNNs) on large scaled graphs. Besides of existed neighbor sampling techniques, scalable methods decoupling graph convolutions and other learnable transformations into preprocessing and post classifier allow normal minibatch training. By replacing redundant concatenation operation with attention mechanism in SIGN, we propose Scalable and Adaptive Graph Neural Networks (SAGN). SAGN can adaptively gather neighborhood information among different hops. To further improve scalable models on semi-supervised learning tasks, we propose Self-Label-Enhance (SLE) framework combining self-training approach and label propagation in depth. We add base model with a scalable node label module. Then we iteratively train models and enhance train set in several stages. To generate input of node label module, we directly apply label propagation based on one-hot encoded label vectors without inner random masking. We find out that empirically the label leakage has been effectively alleviated after graph convolutions. The hard pseudo labels in enhanced train set participate in label propagation with true labels. Experiments on both inductive and transductive datasets demonstrate that, compared with other sampling-based and sampling-free methods, SAGN achieves better or comparable results and SLE can further improve performance.