Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining - Concepts and Techniques.

Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection and matching. In this paper, we propose a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise. We demonstrate through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations. The efficiency is tested on several real-world applications, including object detection and patch-tracking on a smart phone.

ORB: An efficient alternative to SIFT or SURF

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

We present two algorithms for the approximate nearest neighbor problem in high-dimensional spaces. For data sets of size n living in R d , the algorithms require space that is only polynomial in n and d, while achieving query times that are sub-linear in n and polynomial in d. We also show applications to other high-dimensional geometric problems, such as the approximate minimum spanning tree. The article is based on the material from the authors' STOC'98 and FOCS'01 papers. It unifies, generalizes and simplifies the results from those papers.

/pdf/approximate-nearest-neighbors-towards-removing-the-curse-of-27lmlz5prr.pdf

Approximate nearest neighbors: towards removing the curse of dimensionality

XML is rapidly emerging as the new standard for data representation and exchange on the Web. Unlike HTML, tags in XML documents describe the semantics of the data and not how it is to be displayed. In addition, an XML document can be accompanied by a Document Type Descriptor (DTD) which plays the role of a schema for an XML data collection. DTDs contain valuable information on the structure of documents and thus have a crucial role in the efficient storage of XML data, as well as the effective formulation and optimization of XML queries. Despite their importance, however, DTDs are not mandatory, and it is frequently possible that documents in XML databases will not have accompanying DTDs. In this paper, we propose XTRACT, a novel system for inferring a DTD schema for a database of XML documents. Since the DTD syntax incorporates the full expressive power of regular expressions, naive approaches typically fail to produce concise and intuitive DTDs. Instead, the XTRACT inference algorithms employ a sequence of sophisticated steps that involve: (1) finding patterns in the input sequences and replacing them with regular expressions to generate “general” candidate DTDs, (2) factoring candidate DTDs using adaptations of algorithms from the logic optimization literature, and (3) applying the Minimum Description Length (MDL) principle to find the best DTD among the candidates. The results of our experiments with real-life and synthetic DTDs demonstrate the effectiveness of XTRACT's approach in inferring concise and semantically meaningful DTD schemas for XML databases.

/pdf/xtract-learning-document-type-descriptors-from-xml-document-3x3mprr4hf.pdf

XTRACT: Learning Document Type Descriptors from XML Document Collections

We study the problem of predicting the popularity of items in a dynamic environment in which authors post continuously new items and provide feedback on existing items. This problem can be applied to predict popularity of blog posts, rank photographs in a photo-sharing system, or predict the citations of a scientific article using author information and monitoring the items of interest for a short period of time after their creation. As a case study, we show how to estimate the number of citations for an academic paper using information about past articles written by the same author(s) of the paper. If we use only the citation information over a short period of time, we obtain a predicted value that has a correlation of r = 0.57 with the actual value. This is our baseline prediction. Our best-performing system can improve that prediction by adding features extracted from the past publishing history of its authors, increasing the correlation between the actual and the predicted values to r = 0.81.

/pdf/estimating-number-of-citations-using-author-reputation-2jdcr8ucng.pdf

Estimating number of citations using author reputation

Query recommendation is an integral part of modern search engines. The goal of query recommendation is to facilitate users while searching for information. Query recommendation also allows users to explore concepts related to their information needs.In this paper, we present a formal treatment of the problem of query recommendation. In our framework we model the querying behavior of users by a probabilistic reformula- tion graph, or query-flow graph [Boldi et al. CIKM 2008]. A sequence of queries submitted by a user can be seen as a path on this graph. Assigning score values to queries allows us to define suitable utility functions and to consider the expected utility achieved by a reformulation path on the query-flow graph. Providing recommendations can be seen as adding shortcuts in the query-flow graph that "nudge" the reformulation paths of users, in such a way that users are more likely to follow paths with larger expected utility.We discuss in detail the most important questions that arise in the proposed framework. In particular, we provide examples of meaningful utility functions to optimize, we discuss how to estimate the effect of recommendations on the reformulation probabilities, we address the complexity of the optimization problems that we consider, we suggest efficient algorithmic solutions, and we validate our models and algorithms with extensive experimentation. Our techniques can be applied to other scenarios where user behavior can be modeled as a Markov process.

/pdf/an-optimization-framework-for-query-recommendation-nlzc7xuqcl.pdf

An optimization framework for query recommendation

The problem of mining frequent patterns in networks has many applications, including analysis of complex networks, clustering of graphs, finding communities in social networks, and indexing of graphical and biological databases. Despite this wealth of applications, the current state of the art lacks algorithmic tools for counting the number of subgraphs contained in a large network. In this paper we develop data-stream algorithms that approximate the number of all subgraphs of three and four vertices in directed and undirected networks. We use the frequency of occurrence of all subgraphs to prove their significance in order to characterize different kinds of networks: we achieve very good precision in clustering networks with similar structure. The significance of our method is supported by the fact that such high precision cannot be achieved when performing clustering based on simpler topological properties, such as degree, assortativity, and eigenvector distributions. We have also tested our techniques using swap randomization.

https://www.computer.org/csdl/pds/api/csdl/proceedings/download-article/12OmNyaGeEk/pdf

Mining Large Networks with Subgraph Counting

Many genomic sequences and, more generally, (multivariate) time series display tremendous variability. However, often it is reasonable to assume that the sequence is actually generated by or assembled from a small number of sources, each of which might contribute several segments to the sequence. That is, there are h hidden sources such that the sequence can be written as a concatenation of k > h pieces, each of which stems from one of the h sources. We define this (k,h)-segmentation problem and show that it is NP-hard in the general case. We give approximation algorithms achieving approximation ratios of 3 for the L1 error measure and √5 for the L2 error measure, and generalize the results to higher dimensions. We give empirical results on real (chromosome 22) and artificial data showing that the methods work well in practice.

/pdf/finding-recurrent-sources-in-sequences-5d2r5frhrw.pdf

Aristides Gionis

Papers

XTRACT: Learning Document Type Descriptors from XML Document Collections

Estimating number of citations using author reputation

An optimization framework for query recommendation

Mining Large Networks with Subgraph Counting

Finding recurrent sources in sequences