Labeling workflow views with fine-grained dependencies

Abstract

This paper considers the problem of efficiently answering reachability queries over views of provenance graphs, derived from executions of workflows that may include recursion. Such views include composite modules and model fine-grained dependencies between module inputs and outputs. A novel view-adaptive dynamic labeling scheme is developed for efficient query evaluation, in which view specifications are labeled statically (i.e. as they are created) and data items are labeled dynamically as they are produced during a workflow execution. Although the combination of fine-grained dependencies and recursive workflows entail, in general, long (linear-size) data labels, we show that for a large natural class of workflows and views, labels are compact (logarithmic-size) and reachability queries can be evaluated in constant time. Experimental results demonstrate the benefit of this approach over the state-of-the-art technique when applied for labeling multiple views.

Access control and view generation for provenance graphs

“…The problem of answering queries over views of provenance graph is considered in [35]. Views are statically labelled while data items are labelled dynamically as they are produced during a workflow execution.…”

Matching heterogeneous event data

“…All the similarities are initialized in Line 1. From Line 2 to Line 5, we first conduct I rounds of iterations according to formula (1). We consider the early convergence in Line 4, by skipping the iterative computations for those similarities that are early converged.…”

“…Thereby, we observe the total number of iterations w.r.t. all event pairs, i.e., the total times of calculating formula (1). As illustrated in Figure 6(a), the total number of iterations for all event pairs can be significantly reduced by pruning, and the corresponding time costs are reduced in Figure 6(b).…”

“…Therefore, as illustrated in the experimental evaluation in Section 5, our proposed similarity measure with the consideration of dislocation shows higher matching accuracy. Weidlich et al [23] studies matching composite events due to the different levels of granularity of business process [1]. However, it uses label similarity of events to judge m:n matching, which is noneffective on opaque event names.…”

WebLab PROV

“…Other work on fine-grained provenance [7,3] consider a white-box approach exploiting fine-grained descriptions of workflows and services. We consider black-box services for which we infer provenance links by defining fine-grained data dependency mappings between input and output XML fragments.…”