arXiv subjects

Jesse Read

Publications and source records attributed to Jesse Read.

50 records · Page 3Linked to original sources

arXiv2019

Probabilistic Regressor Chains with Monte Carlo Methods

A large number and diversity of techniques have been offered in the literature in recent years for solving multi-label classification tasks, including classifier chains where predictions are cascaded to other models as additional features. The idea of extending this chaining methodology to multi-output regression has already been suggested and trialed: regressor chains. However, this has so-far been limited to greedy inference and has provided relatively poor results compared to individual models, and of limited applicability. In this paper we identify and discuss the main limitations, including an analysis of different base models, loss functions, explainability, and other desiderata of real-world applications. To overcome the identified limitations we study and develop methods for regressor chains. In particular we present a sequential Monte Carlo scheme in the framework of a probabilistic regressor chain, and we show it can be effective, flexible and useful in several types of data. We place regressor chains in context in general terms of multi-output learning with continuous outputs, and in doing this shed additional light on classifier chains.

cs.LG↗

arXiv2019

Perturb and Combine to Identify Influential Spreaders in Real-World Networks

Some of the most effective influential spreader detection algorithms are unstable to small perturbations of the network structure. Inspired by bagging in Machine Learning, we propose the first Perturb and Combine (P&C) procedure for networks. It (1) creates many perturbed versions of a given graph, (2) applies a node scoring function separately to each graph, and (3) combines the results. Experiments conducted on real-world networks of various sizes with the k-core, generalized k-core, and PageRank algorithms reveal that P&C brings substantial improvements. Moreover, this performance boost can be obtained at almost no extra cost through parallelization. Finally, a bias-variance analysis suggests that P&C works mainly by reducing bias, and that therefore, it should be capable of improving the performance of all vertex scoring functions, including stable ones.

cs.SI↗

arXiv2018

Concept-drifting Data Streams are Time Series; The Case for Continuous Adaptation

Learning from data streams is an increasingly important topic in data mining, machine learning, and artificial intelligence in general. A major focus in the data stream literature is on designing methods that can deal with concept drift, a challenge where the generating distribution changes over time. A general assumption in most of this literature is that instances are independently distributed in the stream. In this work we show that, in the context of concept drift, this assumption is contradictory, and that the presence of concept drift necessarily implies temporal dependence; and thus some form of time series. This has important implications on model design and deployment. We explore and highlight the these implications, and show that Hoeffding-tree based ensembles, which are very popular for learning in streams, are not naturally suited to learning \emph{within} drift; and can perform in this scenario only at significant computational cost of destructive adaptation. On the other hand, we develop and parameterize gradient-descent methods and demonstrate how they can perform \emph{continuous} adaptation with no explicit drift-detection mechanism, offering major advantages in terms of accuracy and efficiency. As a consequence of our theoretical discussion and empirical observations, we outline a number of recommendations for deploying methods in concept-drifting streams.

cs.LG↗

arXiv2018

Scikit-Multiflow: A Multi-output Streaming Framework

Scikit-multiflow is a multi-output/multi-label and stream data mining framework for the Python programming language. Conceived to serve as a platform to encourage democratization of stream learning research, it provides multiple state of the art methods for stream learning, stream generators and evaluators. scikit-multiflow builds upon popular open source frameworks including scikit-learn, MOA and MEKA. Development follows the FOSS principles and quality is enforced by complying with PEP8 guidelines and using continuous integration and automatic testing. The source code is publicly available at https://github.com/scikit-multiflow/scikit-multiflow.

cs.LG↗

arXiv2017

Multi-label Classification using Labels as Hidden Nodes

Competitive methods for multi-label classification typically invest in learning labels together. To do so in a beneficial way, analysis of label dependence is often seen as a fundamental step, separate and prior to constructing a classifier. Some methods invest up to hundreds of times more computational effort in building dependency models, than training the final classifier itself. We extend some recent discussion in the literature and provide a deeper analysis, namely, developing the view that label dependence is often introduced by an inadequate base classifier, rather than being inherent to the data or underlying concept; showing how even an exhaustive analysis of label dependence may not lead to an optimal classification structure. Viewing labels as additional features (a transformation of the input), we create neural-network inspired novel methods that remove the emphasis of a prior dependency structure. Our methods have an important advantage particular to multi-label data: they leverage labels to create effective units in middle layers, rather than learning these units from scratch in an unsupervised fashion with gradient-based methods. Results are promising. The methods we propose perform competitively, and also have very important qualities of scalability.

stat.ML↗

arXiv2016

Multi-label Methods for Prediction with Sequential Data

The number of methods available for classification of multi-label data has increased rapidly over recent years, yet relatively few links have been made with the related task of classification of sequential data. If labels indices are considered as time indices, the problems can often be seen as equivalent. In this paper we detect and elaborate on connections between multi-label methods and Markovian models, and study the suitability of multi-label methods for prediction in sequential data. From this study we draw upon the most suitable techniques from the area and develop two novel competitive approaches which can be applied to either kind of data. We carry out an empirical evaluation investigating performance on real-world sequential-prediction tasks: electricity demand, and route prediction. As well as showing that several popular multi-label algorithms are in fact easily applicable to sequencing tasks, our novel approaches, which benefit from a unified view of these areas, prove very competitive against established methods.

cs.LG↗

arXiv2016

Cooperative Parallel Particle Filters for online model selection and applications to Urban Mobility

We design a sequential Monte Carlo scheme for the dual purpose of Bayesian inference and model selection. We consider the application context of urban mobility, where several modalities of transport and different measurement devices can be employed. Therefore, we address the joint problem of online tracking and detection of the current modality. For this purpose, we use interacting parallel particle filters, each one addressing a different model. They cooperate for providing a global estimator of the variable of interest and, at the same time, an approximation of the posterior density of each model given the data. The interaction occurs by a parsimonious distribution of the computational effort, with online adaptation for the number of particles of each filter according to the posterior probability of the corresponding model. The resulting scheme is simple and flexible. We have tested the novel technique in different numerical experiments with artificial and real data, which confirm the robustness of the proposed scheme.

stat.CO↗

arXiv2015

Data Stream Classification using Random Feature Functions and Novel Method Combinations

Big Data streams are being generated in a faster, bigger, and more commonplace. In this scenario, Hoeffding Trees are an established method for classification. Several extensions exist, including high-performing ensemble setups such as online and leveraging bagging. Also, $k$-nearest neighbors is a popular choice, with most extensions dealing with the inherent performance limitations over a potentially-infinite stream. At the same time, gradient descent methods are becoming increasingly popular, owing in part to the successes of deep learning. Although deep neural networks can learn incrementally, they have so far proved too sensitive to hyper-parameter options and initial conditions to be considered an effective `off-the-shelf' data-streams solution. In this work, we look at combinations of Hoeffding-trees, nearest neighbour, and gradient descent methods with a streaming preprocessing approach in the form of a random feature functions filter for additional predictive power. We further extend the investigation to implementing methods on GPUs, which we test on some large real-world datasets, and show the benefits of using GPUs for data-stream learning due to their high scalability. Our empirical evaluation yields positive results for the novel approaches that we experiment with, highlighting important issues, and shed light on promising future directions in approaches to data-stream classification.

cs.LG↗

arXiv2014

Deep Learning for Multi-label Classification

In multi-label classification, the main focus has been to develop ways of learning the underlying dependencies between labels, and to take advantage of this at classification time. Developing better feature-space representations has been predominantly employed to reduce complexity, e.g., by eliminating non-helpful feature attributes from the input space prior to (or during) training. This is an important task, since many multi-label methods typically create many different copies or views of the same input data as they transform it, and considerable memory can be saved by taking advantage of redundancy. In this paper, we show that a proper development of the feature space can make labels less interdependent and easier to model and predict at inference time. For this task we use a deep learning approach with restricted Boltzmann machines. We present a deep network that, in an empirical evaluation, outperforms a number of competitive methods from the literature

cs.LG↗

arXiv2014

Kaggle LSHTC4 Winning Solution

Our winning submission to the 2014 Kaggle competition for Large Scale Hierarchical Text Classification (LSHTC) consists mostly of an ensemble of sparse generative models extending Multinomial Naive Bayes. The base-classifiers consist of hierarchically smoothed models combining document, label, and hierarchy level Multinomials, with feature pre-processing using variants of TF-IDF and BM25. Additional diversification is introduced by different types of folds and random search optimization for different measures. The ensemble algorithm optimizes macroFscore by predicting the documents for each label, instead of the usual prediction of labels per document. Scores for documents are predicted by weighted voting of base-classifier outputs with a variant of Feature-Weighted Linear Stacking. The number of documents per label is chosen using label priors and thresholding of vote scores. This document describes the models and software used to build our solution. Reproducing the results for our solution can be done by running the scripts included in the Kaggle package. A package omitting precomputed result files is also distributed. All code is open source, released under GNU GPL 2.0, and GPL 3.0 for Weka and Meka dependencies.

cs.AI↗

arXiv2013

Efficient Monte Carlo Methods for Multi-Dimensional Learning with Classifier Chains

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance - at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest- performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.

cs.LG↗

arXiv2013

On the flexibility of the design of Multiple Try Metropolis schemes

The Multiple Try Metropolis (MTM) method is a generalization of the classical Metropolis-Hastings algorithm in which the next state of the chain is chosen among a set of samples, according to normalized weights. In the literature, several extensions have been proposed. In this work, we show and remark upon the flexibility of the design of MTM-type methods, fulfilling the detailed balance condition. We discuss several possibilities and show different numerical results.

stat.CO↗

arXiv2012

Improved Adaptive Rejection Metropolis Sampling Algorithms

Markov Chain Monte Carlo (MCMC) methods, such as the Metropolis-Hastings (MH) algorithm, are widely used for Bayesian inference. One of the most important issues for any MCMC method is the convergence of the Markov chain, which depends crucially on a suitable choice of the proposal density. Adaptive Rejection Metropolis Sampling (ARMS) is a well-known MH scheme that generates samples from one-dimensional target densities making use of adaptive piecewise proposals constructed using support points taken from rejected samples. In this work we pinpoint a crucial drawback in the adaptive procedure in ARMS: support points might never be added inside regions where the proposal is below the target. When this happens in many regions it leads to a poor performance of ARMS, with the proposal never converging to the target. In order to overcome this limitation we propose two improved adaptive schemes for constructing the proposal. The first one is a direct modification of the ARMS procedure that incorporates support points inside regions where the proposal is below the target, while satisfying the diminishing adaptation property, one of the required conditions to assure the convergence of the Markov chain. The second one is an adaptive independent MH algorithm with the ability to learn from all previous samples except for the current state of the chain, thus also guaranteeing the convergence to the invariant density. These two new schemes improve the adaptive strategy of ARMS, thus simplifying the complexity in the construction of the proposals. Numerical results show that the new techniques provide better performance w.r.t. the standard ARMS.

stat.CO↗

arXiv2012

A multi-point Metropolis scheme with generic weight functions

The multi-point Metropolis algorithm is an advanced MCMC technique based on drawing several correlated samples at each step and choosing one of them according to some normalized weights. We propose a variation of this technique where the weight functions are not specified, i.e., the analytic form can be chosen arbitrarily. This has the advantage of greater flexibility in the design of high-performance MCMC samplers. We prove that our method fulfills the balance condition, and provide a numerical simulation. We also give new insight into the functionality of different MCMC algorithms, and the connections between them.

stat.CO↗