Noname manuscript No. (will be inserted by the editor) A Survey of Hierarchical Classification Across Different Application Domains

Citations in the corpus

• A Collection of Benchmark Datasets for Systematic Evaluations of Machine Learning on the Semantic Web (2016, background): “Furthermore, as many datasets on the Semantic Web use extensive hierarchies in the form of ontologies, building benchmark datasets for tasks like hierarchical multi-label classification [15] would also be an interesting extension.”
• DEEPre: sequence-based enzyme EC number prediction by deep learning (2017, background): “classification and multi-class classification at the same time, the solutions to the problem can be classified into three categories based on different angles to the problem (Silla and Freitas, 2011), namely, flat classification approach, local classifier approach, and global classifier approach.”
• Chirping up the Right Tree: Incorporating Biological Taxonomies into Deep Bioacoustic Classifiers (2020, background): “The multiclass models can be extended to produce joint probabilities that ensure hierarchical consistency in the model’s predictions, which is crucial for robust hierarchical classification [14].”
• Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL (2020, background): “The training of hierarchical classifiers is a topic with a rich history in the machine learning literature, see for example [53] for a dedicated review and [54] for a recent”
• COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios (2020, unknown): “[9], this taxonomy can be considered a structured tree hierarchy defined over a partially order set (C, ≺), where C is a finite set that enumerates all class concepts in the application domain, and the relation ≺ represents a “IS-A” relationship.”
• Revisiting Knowledge Transfer for Training Object Class Detectors (2017, methodology): “During training they use hierarchical classification [5, 23, 39], which implicitly achieves knowledge transfer somewhere in-between class-generic and class-specific.”
• Weakly-Supervised Hierarchical Text Classification (2018, methodology): “Following the definition in (Silla and Freitas 2010), we consider non-mandatory leaf prediction, wherein documents can be assigned to both internal and leaf categories in the hierarchy.”
• Knowledge graph refinement: A survey of approaches and evaluation methods (2016, methodology): “Despite a larger body of work existing on methods for hierarchical classification [93], there are, to the best of our knowledge, no applications of those methods to knowledge graph completion.”
• A Review on Multi-Label Learning Algorithms (2014, background): “Furthermore, there are alternative multi-label settings where other than a single instance each example is represented by a bag of instances [201], [202] or graphs [87], [89], or extra ontology knowledge might exist on the label space such as hierarchy structure [2], [4], [14], [17], [124], [125], [”
• A hierarchical loss and its problems when classifying non-hierarchically (2017, background): “The columns “aggregate precision,” “aggregate recall,” and “aggregate F1” refer to the hierarchical precision, hierarchical recall, and hierarchical F score detailed in the survey of [11].”
• Machine learning for discovering missing or wrong protein function annotations (2019, methodology): “According to Silla and Freitas [33], the local approach is further divided into three strategies: Local Classifier per Level [3, 5, 14, 25, 30], Local Classifier per Node [7, 9] and Local Classifier per Parent Node [11, 16].”
• Inducing a hierarchy for multi-class classification problems (2021, methodology): “We refer the interested reader to (Silla & Freitas, 2011) for a more detailed discussion on the different types of hierarchical decision rules and ways to train them.”