In this work, we propose an automatic evaluation and comparison of the browsing behavior of Wikipedia readers that can be applied to any language editions of Wikipedia.
Social and Information Networks Computers and Society
Deep convolutional neural networks (CNNs) have been shown to be able to fit a random labeling over data while still being able to generalize well for normal labels.
Recently developed smart pruning algorithms use the DNN response over the training set for a variety of cost functions to determine redundant network weights, leading to less accuracy degradation and possibly less retraining time.
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy.
Acoustical behavior of a room for a given position of microphone and sound source is usually described using the room impulse response.
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers often with little or no drop in classification accuracy.
Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers.
Research in Graph Signal Processing (GSP) aims to develop tools for processing data defined on irregular graph domains.
Visualizing high-dimensional data has been a focus in data analysis communities for decades, which has led to the design of many algorithms, some of which are now considered references (such as t-SNE for example).
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data.
We introduce the Free Music Archive (FMA), an open and easily accessible dataset suitable for evaluating several tasks in MIR, a field concerned with browsing, searching, and organizing large music collections.
In many applications, such geometric data are large and complex (in the case of social networks, on the scale of billions), and are natural targets for machine learning techniques.
We propose a new framework for the analysis of low-rank tensors which lies at the intersection of spectral graph theory and signal processing.
Sparsity exploiting image reconstruction (SER) methods have been extensively used with Total Variation (TV) regularization for tomographic reconstructions.
In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs.
Ranked #4 on Skeleton Based Action Recognition on SBU
Graph-based methods for signal processing have shown promise for the analysis of data exhibiting irregular structure, such as those found in social, transportation, and sensor networks.
We cast the problem of source localization on graphs as the simultaneous problem of sparse recovery and diffusion kernel learning.
This makes the sinogram an ideal candidate for graph based denoising since it generally has a piecewise smooth structure.
Accordingly, we suggest a new way to incorporate a notion of locality, and develop local uncertainty principles that bound the concentration of the analysis coefficients of each atom of a localized graph spectral filter frame in terms of quantities that depend on the local structure of the graph around the center vertex of the given atom.
We introduce a novel framework for an approxi- mate recovery of data matrices which are low-rank on graphs, from sampled measurements.
Graphs are a central tool in machine learning and information processing as they allow to conveniently capture the structure of complex datasets.
This work formulates a novel song recommender system as a matrix completion problem that benefits from collaborative filtering through Non-negative Matrix Factorization (NMF) and content-based filtering via total variation (TV) on graphs.
We build upon recent advances in graph signal processing to propose a faster spectral clustering algorithm.
Social and Information Networks Numerical Analysis
Signal-processing on graphs has developed into a very active field of research during the last decade.
Clustering experiments on 7 benchmark datasets with different types of corruptions and background separation experiments on 3 video datasets show that our proposed model outperforms 10 state-of-the-art dimensionality reduction models.
Principal Component Analysis (PCA) is the most widely used tool for linear dimensionality reduction and clustering.
Feature descriptors play a crucial role in a wide range of geometry analysis and processing applications, including shape correspondence, retrieval, and segmentation.
In this paper, we consider the problem of finding dense intrinsic correspondence between manifolds using the recently introduced functional framework.
Our main goal is thus to find a low-rank solution that is structured by the proximities of rows and columns encoded by graphs.
Ranked #13 on Recommendation Systems on MovieLens 100K (using extra training data)
We show that the Gaussian prior leads to an efficient representation that favors the smoothness property of the graph signals.
Convex optimization is an essential tool for machine learning, as many of its problems can be formulated as minimization problems of specific objective functions.
Inspired by the recently proposed Magnetic Resonance Fingerprinting (MRF) technique, we develop a principled compressed sensing framework for quantitative MRI.
Information Theory Information Theory
The background image is common to all observed images but undergoes geometric transformations, as the scene is observed from different viewpoints.
In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs.
We propose a novel method for constructing wavelet transforms of functions defined on the vertices of an arbitrary finite weighted graph.
Functional Analysis Information Theory Information Theory 42C40; 65T90