Dimensional Reweighting Graph Convolutional Networks
arXiv:1907.02237
Abstract
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.
arXiv commentWe decide to drastically modify the article so we don't wish to let this outdated version continue to confuse readers
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Neural Networks as Gaussian Processes
- Layer Normalization
- More is the Same; Phase Transitions and Mean Field Theories
- MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
- GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
- Adaptive Sampling Towards Fast Graph Representation Learning
- GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
- Dual-Primal Graph Convolutional Networks
- Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization