Graph Entropy Minimization for Semi-supervised Node Classification

31 May 2023  ·  Yi Luo, Guangchun Luo, Ke Qin, Aiguo Chen ·

Node classifiers are required to comprehensively reduce prediction errors, training resources, and inference latency in the industry. However, most graph neural networks (GNN) concentrate only on one or two of them. The compromised aspects thus are the shortest boards on the bucket, hindering their practical deployments for industrial-level tasks. This work proposes a novel semi-supervised learning method termed Graph Entropy Minimization (GEM) to resolve the three issues simultaneously. GEM benefits its one-hop aggregation from massive uncategorized nodes, making its prediction accuracy comparable to GNNs with two or more hops message passing. It can be decomposed to support stochastic training with mini-batches of independent edge samples, achieving extremely fast sampling and space-saving training. While its one-hop aggregation is faster in inference than deep GNNs, GEM can be further accelerated to an extreme by deriving a non-hop classifier via online knowledge distillation. Thus, GEM can be a handy choice for latency-restricted and error-sensitive services running on resource-constraint hardware. Code is available at https://github.com/cf020031308/GEM.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification CiteSeer with Public Split: fixed 20 nodes per class GEM Accuracy 74.2 # 9
Node Classification CiteSeer with Public Split: fixed 20 nodes per class EEM Accuracy 72.63 # 24
Node Classification CiteSeer with Public Split: fixed 20 nodes per class OKDEEM Accuracy 73.53 # 13
Node Classification Cora with Public Split: fixed 20 nodes per class GEM Accuracy 83.05% # 20
Node Classification PubMed with Public Split: fixed 20 nodes per class GEM Accuracy 78.48 # 24
Node Classification PubMed with Public Split: fixed 20 nodes per class Graph-MLP Accuracy 79.91 # 17

Methods


No methods listed for this paper. Add relevant methods here