Tgk Toon Calders

Mining All Non-derivable Frequent Itemsets

Recent studies on frequent itemset mining algorithms resulted in significant performance improvements. However, if the minimal support threshold is set too low, or the data is highly correlated, the number of frequent itemsets itself can be prohibitively large. To overcome this problem, recently several proposals have been made to construct a concise representation of the frequent itemsets, instead of mining all frequent itemsets. The main goal of this paper is to identify redundancies in the set of all frequent itemsets and to exploit these redundancies in order to reduce the result of a mining operation. We present deduction rules to derive tight bounds on the support of candidate itemsets. We show how the deduction rules allow for constructing a minimal representation for all frequent itemsets. We also present connections between our proposal and recent proposals for concise representations and we give the results of experiments on real-life datasets that show the effectiveness of the deduction rules. In fact, the experiments even show that in many cases, first mining the concise representation, and then creating the frequent itemsets from this representation outperforms existing frequent set mining algorithms.

Three naive Bayes approaches for discrimination-free classification

In this paper, we investigate how to modify the naive Bayes classifier in order to perform classification that is restricted to be independent with respect to a given sensitive attribute. Such independency restrictions occur naturally when the decision process leading to the labels in the data-set was biased; e.g., due to gender or racial discrimination. This setting is motivated by many cases in which there exist laws that disallow a decision that is partly based on discrimination. Naive application of machine learning techniques would result in huge fines for companies. We present three approaches for making the naive Bayes classifier discrimination-free: (i) modifying the probability of the decision being positive, (ii) training one model for every sensitive attribute value and balancing them, and (iii) adding a latent variable to the Bayesian model that represents the unbiased label and optimizing the model parameters for likelihood using expectation maximization. We present experiments for the three approaches on both artificial and real-life data.

Non-derivable itemset mining

All frequent itemset mining algorithms rely heavily on the monotonicity principle for pruning. This principle allows for excluding candidate itemsets from the expensive counting phase. In this paper, we present sound and complete deduction rules to derive bounds on the support of an itemset. Based on these deduction rules, we construct a condensed representation of all frequent itemsets, by removing those itemsets for which the support can be derived, resulting in the so called Non-Derivable Itemsets (NDI) representation. We also present connections between our proposal and recent other proposals for condensed representations of frequent itemsets. Experiments on real-life datasets show the effectiveness of the NDI representation, making the search for frequent non-derivable itemsets a useful and tractable alternative to mining all frequent itemsets.

Discrimination Aware Decision Tree Learning

Recently, the following discrimination aware classification problem was introduced: given a labeled dataset and an attribute B, find a classifier with high predictive accuracy that at the same time does not discriminate on the basis of the given attribute B. This problem is motivated by the fact that often available historic data is biased due to discrimination, e.g., when B denotes ethnicity. Using the standard learners on this data may lead to wrongfully biased classifiers, even if the attribute B is removed from training data. Existing solutions for this problem consist in “cleaning away” the discrimination from the dataset before a classifier is learned. In this paper we study an alternative approach in which the non-discrimination constraint is pushed deeply into a decision tree learner by changing its splitting criterion and pruning strategy. Experimental evaluation shows that the proposed approach advances the state-of-the-art in the sense that the learned decision trees have a lower discrimination than models provided by previous methods, with little loss in accuracy.

Minimal k-Free Representations of Frequent Sets

Due to the potentially immense amount of frequent sets that can be generated from transactional databases, recent studies have demonstrated the need for concise representations of all frequent sets. These studies resulted in several successful algorithms that only generate a lossless subset of the frequent sets. In this paper, we present a unifying framework encapsulating most known concise representations. Because of the deeper understanding of the different proposals thus obtained, we are able to provide new, provably more concise, representations. These theoretical results are supported by several experiments showing the practical applicability.

Classifying without discriminating

Classification models usually make predictions on the basis of training data. If the training data is biased towards certain groups or classes of objects, e.g., there is racial discrimination towards black people, the learned model will also show discriminatory behavior towards that particular community. This partial attitude of the learned model may lead to biased outcomes when labeling future unlabeled data objects. Often, however, impartial classification results are desired or even required by law for future data objects in spite of having biased training data. In this paper, we tackle this problem by introducing a new classification scheme for learning unbiased models on biased training data. Our method is based on massaging the dataset by making the least intrusive modifications which lead to an unbiased dataset. On this modified dataset we then learn a non-discriminating classifier. The proposed method has been implemented and experimental results on a credit approval dataset show promising results: in all experiments our method is able to reduce the prejudicial behavior for future classification significantly without loosing too much predictive accuracy.

Using minimum description length for process mining

In the field of process mining, the goal is to automatically extract process models from event logs. Recently, many algorithms have been proposed for this task. For comparing these models, different quality measures have been proposed. Most of these measures, however, have several disadvantages; they are model-dependent, assume that the model that generated the log is known, or need negative examples of event sequences. In this paper we propose a new measure, based on the minimal description length principle, to evaluate the quality of process models that does not have these disadvantages. To illustrate the properties of the new measure we conduct experiments and discuss the trade-off between model complexity and compression.

Data preprocessing techniques for classification without discrimination

Recently, the following Discrimination-Aware Classification Problem was introduced: Suppose we are given training data that exhibit unlawful discrimination; e.g., toward sensitive attributes such as gender or ethnicity. The task is to learn a classifier that optimizes accuracy, but does not have this discrimination in its predictions on test data. This problem is relevant in many settings, such as when the data are generated by a biased decision process or when the sensitive attribute serves as a proxy for unobserved features. In this paper, we concentrate on the case with only one binary sensitive attribute and a two-class classification problem. We first study the theoretically optimal trade-off between accuracy and non-discrimination for pure classifiers. Then, we look at algorithmic solutions that preprocess the data to remove discrimination before a classifier is learned. We survey and extend our existing data preprocessing techniques, being suppression of the sensitive attribute, massaging the dataset by changing class labels, and reweighing or resampling the data to remove discrimination without relabeling instances. These preprocessing techniques have been implemented in a modified version of Weka and we present the results of experiments on real-life data.

Introduction to the special section on educational data mining

Educational Data Mining (EDM) is an emerging multidisciplinary research area, in which methods and techniques for exploring data originating from various educational information systems have been developed. EDM is both a learning science, as well as a rich application area for data mining, due to the growing availability of educational data. EDM contributes to the study of how students learn, and the settings in which they learn. It enables data-driven decision making for improving the current educational practice and learning material. We present a brief overview of EDM and introduce four selected EDM papers representing a crosscut of different application areas for data mining in education.

Building Classifiers with Independency Constraints

In this paper we study the problem of classifier learning where the input data contains unjustified dependencies between some data attributes and the class label. Such cases arise for example when the training data is collected from different sources with different labeling criteria or when the data is generated by a biased decision process. When a classifier is trained directly on such data, these undesirable dependencies will carry over to the classifier’s predictions. In order to tackle this problem, we study the classification with independency constraints problem: find an accurate model for which the predictions are independent from a given binary attribute. We propose two solutions for this problem and present an empirical validation.