Sequential pattern mining is a well-studied data mining task with wide applications. However, fine-tuning the minsup parameter of sequential pattern mining algorithms to generate enough patterns is difficult and timeconsuming. To address this issue, the task of top-k sequential pattern mining has been defined, where k is the number of sequential patterns to be found, and is set by the user. In ...

We introduce a diversified top-k partial MaxSAT problem, a combination of partial MaxSAT problem and enumeration problem. Given a partial MaxSAT formula F and a positive integer k, the diversified top-k partial MaxSAT is to find k maximal solutions for F such that the k maximal solutions satisfy the maximum number of soft clauses of F . This problem can be widely used in many applications inclu...

Top-k queries on large multi-attribute data sets are fundamental operations in information retrieval and ranking applications. In this paper, we initiate research on the anytime behavior of top-k algorithms. In particular, given specific top-k algorithms (TA and TASorted) we are interested in studying their progress toward identification of the correct result at any point during the algorithms’...

In this paper we describe a tool named top-k aggregator. Using this tool we can retrieve some best objects with respect to user requirements. User can say which values of properties of offers (e.g. salary, education requirement, place, working hours per week) are interesting for him or her, how much and also which are not interesting. Another form of user specification can be made by evaluation...

Class ambiguity is typical in image classification problems with a large number of classes. When classes are difficult to discriminate, it makes sense to allow k guesses and evaluate classifiers based on the top-k error instead of the standard zero-one loss. We propose top-k multiclass SVM as a direct method to optimize for top-k performance. Our generalization of the well-known multiclass SVM ...

Recommender systems have been widely used in e-commerce applications. They are a subclass of information filtering system, used to either predict whether a user will prefer an item (prediction problem) or identify a set of k items that will be user-interest (Top-k recommendation problem). Demanding sufficient ratings to make robust predictions and suggesting qualified recommendations are two si...

We propose an efficient Frequent Sequence Stream algorithm for identifying the top k most frequent subsequences over big data streams. Our Sequence Stream algorithm gains its efficiency by its time complexity of linear time and very limited space complexity. With a pre-specified subsequence window size S and the k value, in very high probabilities, the Sequence Stream algorithm retrieve the top...

Recently, there has been considerable interest in efficiently computing strongly correlated pairs in large databases. Most previous studies require the specification of a minimum correlation threshold to perform the computation. However, it may be difficult for users to provide an appropriate threshold in practice, since different data sets typically have different characteristics. To this end,...

ListNet is a well-known listwise learning to rank model and has gained much attention in recent years. A particular problem of ListNet, however, is the high computation complexity in model training, mainly due to the large number of object permutations involved in computing the gradients. This paper proposes a stochastic ListNet approach which computes the gradient within a bounded permutation ...

Ensemble methods such as AdaBoost are popular machine learning methods that create highly accurate classifier by combining the predictions from several classifiers. We present a parametrized method of AdaBoost that we call Top-k Parametrized Boost. We evaluate our and other popular ensemble methods from a classification perspective on several real datasets. Our empirical study shows that our me...