Graph-Based Discrete Differential Geometry for Critical Instance Filtering
نویسنده
چکیده
Graph theory has been shown to provide a powerful tool for representing and tackling machine learning problems, such as clustering, semi-supervised learning, and feature ranking. This paper proposes a graph-based discrete differential operator for detecting and eliminating competence-critical instances and class label noise from a training set in order to improve classification performance. Results of extensive experiments on artificial and real-life classification problems substantiate the effectiveness of the proposed approach.
منابع مشابه
Generating Discrete Trace Transition System of a Polyhe-dral Invariant Hybrid Automaton
Supervisory control and fault diagnosis of hybrid systems need to have complete information about the discrete states transitions of the underling system. From this point of view, the hybrid system should be abstracted to a Discrete Trace Transition System (DTTS) and represented by a discrete mode transition graph. In this paper an effective method is proposed for generating discrete mode trans...
متن کاملDivergence Analysis of Discrete 2-d Shapes
In this paper we introduce a second order differential operator in order to partition discrete objects into meaningful parts. One of these parts contains all points of the object’s medial axis which is a widely used shape descriptor. Since aliasing is a fundamental problem for methods based on the boundary of discrete objects we use a bilateral filter to reduce the artefacts significantly. As a...
متن کاملFrom Graph Transformations to Differential Equations
In a variety of disciplines models are used to predict, measure or explain quantitative properties. Examples include the concentration of a chemical substance produced within a given period, the growth of the size of a population of individuals, the time taken to recover from a communication breakdown in a network, etc. The models such properties arise from are often discrete and structural in ...
متن کاملDiscrete Regularization on Weighted Graphs for Image and Mesh Filtering
We propose a discrete regularization framework on weighted graphs of arbitrary topology, which unifies image and mesh filtering. The approach considers the problem as a variational one, which consists in minimizing a weighted sum of two energy terms: a regularization one that uses the discrete p-Laplace operator, and an approximation one. This formulation leads to a family of simple nonlinear f...
متن کاملDifferentially private instance-based noise mechanisms in practice
Differential privacy is a widely used privacy model today, whose privacy guarantees are obtained to the price of a random perturbation of the result. In some situations, basic differentially private mechanisms may add too much noise to reach a reasonable level of privacy. To answer this shortcoming, several works have provided more technically involved mechanisms, using a new paradigm of differ...
متن کامل