Diversity-Driven Widening of Hierarchical Agglomerative Clustering

Fillbrunn, Alexander; Berthold, Michael R.

doi:10.1007/978-3-319-24465-5_8

Cited by 8 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The widening framework terms this Top-k-widening, i.e., M i+1 = s T op−k (r(M i )) : |M i+1 | = k. WIDENING begins to widen the search paths beyond a simple greedy mechanism when diversity is brought into play. The notion of diversity can be implemented in either the refining step as in [24,25] or in the selection step as in [11,12]. Given a diverse refinement operator, r ∆ (•), as in [24,25], where a diversity function, ∆, is imposed on the output, DIVERSE TOP-K WIDENING is described by…”

Section: Wideningmentioning

confidence: 99%

“…Not Faster." Although the demonstrated examples, such as WIDENED KRIMP [24], WIDENED HIERARCHICAL CLUS-TERING [11], WIDENED BAYESIAN NETWORKS [25] and BUCKET SELECTION [12] have been able to find superior solutions, i.e., "better," they have been unable to demonstrate this ability in a run-time that is comparable to the standard versions of the greedy algorithms. "Not faster" is not intended to mean "slower.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Communication-Free Widened Learning of Bayesian Network Classifiers Using Hashed Fiedler Vectors

Sampson

Borgelt

Berthold

2018

Advances in Intelligent Data Analysis XVII

Self Cite

View full text Add to dashboard Cite

Widening is a method where parallel resources are used to find better solutions from greedy algorithms instead of merely trying to find the same solutions more quickly. To date, every example of Widening has used some form of communication between the parallel workers to maintain their distances from one another in the model space. For the first time, we present a communication-free, widened extension to a standard machine learning algorithm. By using Locality Sensitive Hashing on the Bayesian networks' Fiedler vectors, we demonstrate the ability to learn classifiers superior to those of standard implementations and to those generated with a greedy heuristic alone.

show abstract

Section: Wideningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Communication-Free Widened Learning of Bayesian Network Classifiers Using Hashed Fiedler Vectors

Sampson

Borgelt

Berthold

2018

Advances in Intelligent Data Analysis XVII

Self Cite

View full text Add to dashboard Cite

show abstract

“…For set covering Ivanova et al [9] use the Jaccard coefficient, Sampson et al use the Frobenius Norm of the difference of the graphs' Laplacians to compare Bayesian networks [12] and an optimization based on p-dispersion-min-sum for KRIMP [13]. Fillbrunn et al [7] compare incomplete hierarchical clustering trees by using the Robinson-Foulds metric. Most selection strategies presented in those publications are either computationally too expensive to be feasible for use in greedy algorithms due to them having to sort the models or build distance matrices, or they require extensive communication between workers.…”

Section: Related Workmentioning

confidence: 99%

“…Nevertheless, widening has shown very promising results for problems that have a suitable model-dependent distance measure. Examples of such problems include the set cover problem [9], KRIMP [12], Bayesian networks [13], and hierarchical agglomerative clustering [7].…”

Section: Introductionmentioning

confidence: 99%

Bucket Selection: A Model-Independent Diverse Selection Strategy for Widening

Fillbrunn

Wörteler

Grossniklaus

et al. 2017

Advances in Intelligent Data Analysis XVI

Self Cite

View full text Add to dashboard Cite

When using a greedy algorithm for finding a model, as is the case in many data mining algorithms, there is a risk of getting caught in local extrema, i.e., suboptimal solutions. Widening is a technique for enhancing greedy algorithms by using parallel resources to broaden the search in the model space. The most important component of widening is the selector, a function that chooses the next models to refine. This selector ideally enforces diversity within the selected set of models in order to ensure that parallel workers explore sufficiently different parts of the model space and do not end up mimicking a simple beam search. Previous publications have shown that this works well for problems with a suitable distance measure for the models, but if no such measure is available, applying widening is challenging. In addition these approaches require extensive, sequential computations for diverse subset selection, making the entire process much slower than the original greedy algorithm. In this paper we propose the bucket selector, a model-independent randomized selection strategy. We find that (a) the bucket selector is a lot faster and not significantly worse when a diversity measure exists and (b) it performs better than existing selection strategies in cases without a diversity measure.

show abstract

“…This enables the system as a whole to avoid local optima and potentially find better models than the greedy learning algorithm would otherwise find. Previous work [13,29] has demonstrated its viability on real world algorithms. This work builds on that with an application to the superexponentially-sized [28] hypothesis space of learning Bayesian Networks.…”

Section: Introductionmentioning

confidence: 99%

Widened Learning of Bayesian Network Classifiers

Sampson

Berthold

2016

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. We demonstrate the application of Widening to learning performant Bayesian Networks for use as classifiers. Widening is a framework for utilizing parallel resources and diversity to find models in a hypothesis space that are potentially better than those of a standard greedy algorithm. This work demonstrates that widened learning of Bayesian Networks, using the Frobenius Norm of the networks' graph Laplacian matrices as a distance measure, can create Bayesian networks that are better classifiers than those generated by popular Bayesian Network algorithms.

show abstract

Diversity-Driven Widening of Hierarchical Agglomerative Clustering

Cited by 8 publications

References 17 publications

Communication-Free Widened Learning of Bayesian Network Classifiers Using Hashed Fiedler Vectors

Communication-Free Widened Learning of Bayesian Network Classifiers Using Hashed Fiedler Vectors

Bucket Selection: A Model-Independent Diverse Selection Strategy for Widening

Widened Learning of Bayesian Network Classifiers

Contact Info

Product

Resources

About