1,720,987 research outputs found
CAGE: Constrained deep Attributed Graph Embedding
No full textIn this paper we deal with complex attributed graphs which can exhibit rich connectivity patterns and whose nodes are often associated with attributes, such as text or images. In order to analyze these graphs, the primary challenge is to find an effective way to represent them by preserving both structural properties and node attribute information. To create low-dimensional and meaningful embedded representations of these complex graphs, we propose a fully unsupervised model based on Deep Learning architectures, called Constrained Attributed Graph Embedding model (CAGE). The main contribution of the proposed model is the definition of a novel two-phase optimization problem that explicitly models node attributes to obtain a higher representation expressiveness while preserving the local and the global structural properties of the graph. We validated our approach on two different benchmark datasets for node classification. Experimental results demonstrate that this novel representation provides significant improvements compared to state of the art approaches, also showing higher robustness with respect to the size of the training data
A Particle Filtering Approach for Tracking an Unknown Number of Objects with Dynamic Relations
No full textIn recent years there has been a growing interest on particle filters for solving tracking problems, thanks to their applicability to problems with continuous, non-linear and non-Gaussian state spaces, which makes them more suited than hidden Markov models, Kalman filters and their derivations, in many real world tasks. Applications include video surveillance, sensor fusion, tracking positions and behaviors of moving objects, situation assessment in civil and bellic scenarios, econometric and clinical data series analysis. In many environments it is possible to recognize classes of similar entities, like pedestrians or vehicles in a video surveillance system, or commodities in econometric. In this paper, a relational particle filter for tracking an unknown number of objects is presented which exploits possible interactions between objects to improve the quality of filtering. We will see that taking into account relations between objects will ease the tracking of objects in presence of occlusions and discontinuities in object dynamics. Experimental results on a benchmark data set are presented. © 2012 Springer Science+Business Media Dordrecht
Classification methods based on k-logistic models
No full textLogistic regression is a simple yet effective technique widely used in machine learning with applications spanning various scientific fields. In this paper, we introduce new logistic regression models based on the k-exponential function derived from k-statistical theory, which approaches the standard exponential function as its parameter k tends to zero. We propose models for both binary and multivariate classification, demonstrating that they extend traditional logistic regression while maintaining the same computational complexity as conventional logistic classifiers. Computational experiments on diverse benchmark data sets show that our k-logistic classifiers outperform standard logistic regression models in the vast majority of cases
LearningToAdapt with word embeddings: domain adaptation of named entity recognition systems
No full textThe task of Named Entity Recognition (NER) is aimed at identifying named entities in a given text and classifying them into pre-defined domain entity types such as persons, organizations, locations. Most of the existing NER systems make use of generic entity type classification schemas, however, the comparison and integration of (more or less) different entity types among different NER systems is a complex problem even for human experts. In this paper, we propose a supervised approach called L2AWE (Learning To Adapt with Word Embeddings) which aims at adapting a NER system trained on a source classification schema to a given target one. In particular, we validate the hypothesis that the embedding representation of named entities can improve the semantic meaning of the feature space used to perform the adaptation from a source to a target domain. The results obtained on benchmark datasets of informal text show that L2AWE not only outperforms several state of the art models, but it is also able to tackle errors and uncertainties given by NER systems
- …
