Graph Quantization

2010/01/06 by Brijnesh J. Jain, Jain, Brijnesh J., Klaus Obermayer +1 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #cs.AI

paper · pdf · doi:10.48550/arxiv.1001.0921

24 pages; submitted to CVIU

arxiv created 2010/01/06 · arxiv updated 2010/01/14

Abstract

Vector quantization(VQ) is a lossy data compression technique from signal processing, which is restricted to feature vectors and therefore inapplicable for combinatorial structures. This contribution presents a theoretical foundation of graph quantization (GQ) that extends VQ to the domain of attributed graphs. We present the necessary Lloyd-Max conditions for optimality of a graph quantizer and consistency results for optimal GQ design based on empirical distortion measures and stochastic optimization. These results statistically justify existing clustering algorithms in the domain of graphs. The proposed approach provides a template of how to link structural pattern recognition methods other than GQ to statistical pattern recognition.

Cited by

• Learning in Riemannian Orbifolds

Related

• Accelerating Competitive Learning Graph Quantization
• Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
• VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
• Degree-Quant: Quantization-Aware Training for Graph Neural Networks
• \rm A²Q: Aggregation-Aware Quantization for Graph Neural Networks