Dimensional Reweighting Graph Convolutional Networks
This addresses a specific bottleneck in GCNs for node classification tasks, offering an incremental improvement that can be combined with existing techniques.
The paper tackles the problem of dimensional information imbalance in Graph Convolutional Networks (GCNs) by proposing Dimensional Reweighting GCN (DrGCN), which improves stability and achieves superior performance on benchmark and industrial datasets.
Graph Convolution Networks (GCNs) are becoming more and more popular for learning node representations on graphs. Though there exist various developments on sampling and aggregation to accelerate the training process and improve the performances, limited works focus on dealing with the dimensional information imbalance of node representations. To bridge the gap, we propose a method named Dimensional reweighting Graph Convolution Network (DrGCN). We theoretically prove that our DrGCN can guarantee to improve the stability of GCNs via mean field theory. Our dimensional reweighting method is very flexible and can be easily combined with most sampling and aggregation techniques for GCNs. Experimental results demonstrate its superior performances on several challenging transductive and inductive node classification benchmark datasets. Our DrGCN also outperforms existing models on an industrial-sized Alibaba recommendation dataset.