Feature selection plays a crucial role in machine learning, as it eliminates data noise and redundancy, thereby significantly reducing computational complexity and enhancing the overall performance of the model. The challenges of feature selection for hybrid information systems stem from the difficulty in quantifying the disparities among nominal attribute values. Furthermore, a significant majority of the current methodologies exhibit sensitivity to noise. This paper introduces techniques that address the aforementioned issues from the perspective of fuzzy evidence theory. First of all, a new distance incorporating decision attributes is defined, and then a relation between fuzzy evidence theory and fuzzy $$\beta $$β covering with an anti-noise mechanism is established. In this framework, two robust feature selection algorithms for hybrid data are proposed based on fuzzy belief and fuzzy plausibility. Experiments on 10 data sets of various types show that compared with the other 6 state-of-the-art algorithms, the proposed algorithms improve the anti-noise ability by at least 6% with higher average classification accuracy. Therefore, it can be concluded that the proposed algorithms have excellent anti-noise ability while maintaining good feature selection ability.

Continuous Integration pipelines rely on large-scale automated testing to support rapid releases. However, flaky tests exhibit non-deterministic outcomes under an identical code and configuration, substantially increasing rerun costs and hindering fault localization. Existing approaches struggle to uniformly model heterogeneous runtime evidence and its multi-relational structure in CI environments, which limits cross-project generalization and interpretability. To address this gap, this paper presents HgtFlaky, a runtime-evidence-centered multi-view heterogeneous graph learning framework. A Unified Event Model is introduced to normalize heterogeneous CI artifacts into semantically consistent event quadruples, and a heterogeneous execution graph is then constructed to capture testing entities and multiple relation types. Based on the HEG, three complementary views are derived to characterize run-level, test-level, and thread-level flaky behaviors. A heterogeneous graph Transformer is further adopted to jointly encode the multi-view graph instances and learn transferable test-level representations for flaky/non-flaky prediction. Experiments on two benchmark datasets, FlakeFlagger and IDoFT, show that HgtFlaky achieves strong and stable performance. Under 10-fold cross-validation, it obtains an F1-score of 83% on FlakeFlagger and 98% on IDoFT. Under per-project validation on FlakeFlagger, HgtFlaky achieves 78% Precision, 89% Recall, and 81% F1-score, outperforming Flakify by 8 percentage points and FlakeFlagger by 74 percentage points in F1-score.