Softening Discrete Relaxation
Andrew Finch, Richard C. Wilson, Edwin R. Hancock · Neural Information Processing Systems · 1996
This paper describes a new framework for relational graph matching. The starting point is a recently reported Bayesian consistency measure which gauges structural differences using Hamming distance. The main contributions of the work are threefold. Firstly, we demonstrate how the discrete components of the cost function can be softened. The second contribution is to show how the softened cost function can be used to locate matches using continuous non-linear optimisation. Finally, we show how the resulting graph matching algorithm relates to the standard quadratic assignment problem.