Kernel methods provide a convenient way to apply a wide range of learning techniques to complex and structured data by shifting the representational problem from one of finding an embedding of the data to that of defining a positive semi-definite kernel. One problem with the most widely used kernels is that they neglect the locational information within the structures, resulting in less discrimination. Correspondence-based kernels, on the other hand, are in general more discriminating, at the cost of sacrificing positive-definiteness due to their inability to guarantee transitivity of the correspondences between multiple graphs. In this paper we adopt a general framework for the projection of (relaxed) correspondences onto the space of transitive correspondences, thus transforming any given matching algorithm onto a transitive multi-graph matching approach. The resulting transitive correspondences can then be used to provide a kernel that both maintains locational information and is guaranteed to be positive-definite. Experimental evaluation validates the effectiveness of the kernel for several structural classification tasks.

Kernel methods provide a convenient way to apply a wide range of learning techniques to complex and structured data by shifting the representational problem from one of finding an embedding of the data to that of defining a positive semi-definite kernel. One problem with the most widely used kernels is that they neglect the locational information within the structures, resulting in less discrimination. Correspondence-based kernels, on the other hand, are in general more discriminating, at the cost of sacrificing positive-definiteness due to their inability to guarantee transitivity of the correspondences between multiple graphs. In this paper we adopt a general framework for the projection of (relaxed) correspondences onto the space of transitive correspondences, thus transforming any given matching algorithm onto a transitive multi-graph matching approach. The resulting transitive correspondences can then be used to provide a kernel that both maintains locational information and is guaranteed to be positive-definite. Experimental evaluation validates the effectiveness of the kernel for several structural classification tasks.

Transitive Assignment Kernels for Structural Classification

SCHIAVINATO, MICHELE;GASPARETTO, ANDREA;TORSELLO, Andrea
2015

Abstract

Kernel methods provide a convenient way to apply a wide range of learning techniques to complex and structured data by shifting the representational problem from one of finding an embedding of the data to that of defining a positive semi-definite kernel. One problem with the most widely used kernels is that they neglect the locational information within the structures, resulting in less discrimination. Correspondence-based kernels, on the other hand, are in general more discriminating, at the cost of sacrificing positive-definiteness due to their inability to guarantee transitivity of the correspondences between multiple graphs. In this paper we adopt a general framework for the projection of (relaxed) correspondences onto the space of transitive correspondences, thus transforming any given matching algorithm onto a transitive multi-graph matching approach. The resulting transitive correspondences can then be used to provide a kernel that both maintains locational information and is guaranteed to be positive-definite. Experimental evaluation validates the effectiveness of the kernel for several structural classification tasks.
Third International Workshop on Similarity-Based Pattern Recognition - SIMBAD 2015
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10278/3661958
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 4
social impact