Accelerating Competitive Learning Graph Quantization

2010/01/06 by Brijnesh J. Jain, Jain, Brijnesh J., Klaus Obermayer +1
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1001.0927

17 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 for which simple competitive learning is one standard method to quantize patterns from the input space. Extending competitive learning VQ to the domain of graphs results in competitive learning for quantizing input graphs. In this contribution, we propose an accelerated version of competitive learning graph quantization (GQ) without trading computational time against solution quality. For this, we lift graphs locally to vectors in order to avoid unnecessary calculations of intractable graph distances. In doing so, the accelerated version of competitive learning GQ gradually turns locally into a competitive learning VQ with increasing number of iterations. Empirical results show a significant speedup by maintaining a comparable solution quality.

Related

• Graph Quantization
• VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
• Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
• Optimal and Near-Optimal Adaptive Vector Quantization
• A Survey of Quantized Graph Representation Learning: Connecting Graph Structures with Large Language Models