Leveraging Sequence Classification by Taxonomy-Based Multitask Learning

By Christian Widmer, Jose Leiva, Yasemin Altun, Gunnar Rätsch. 2010

85 citations recorded by the source corpus.

Subfields: Molecular Biology, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Natural Language Processing

Citations in the corpus

An Overview of Multi-task Learning (2018, methodology): “Applications of MTL in bioinformatics and health informatics include organism modeling [101], mechanism identification of response to therapeutic targets [102], cross-platform siRNA efficacy prediction [103], detection of causal genetic markers through association analysis of multiple”
A Survey on Multi-Task Learning (2017, background): “In [163], several regularized multi-task models are proposed to utilize the hierarchical structure among tasks to model organisms.”
Feature-based transfer learning with real-world applications (2010, background): “In Bioinformatics, motivated by that different biological entities, such as organisms, genes, etc, may be related to each other from a biological point of view, some research works have been proposed to apply transfer learning techniques to solve various computational biological problems, such as id”
Multitask Matrix Completion for Learning Protein Interactions Across Diseases (2016, unknown): “IMC [9, 16]: This is the link-prediction model from Section 2, where data from all tasks is combined without incorporating any task relationships (comparable to the ‘union’ setting from [28]).”
Recursive regularization for large-scale classification with hierarchical and graphical dependencies (2013, methodology): “Our proposed schemes achieve state-of-the-art results on multiple benchmark datasets which are orders of magnitudes (∼ 1000x) larger than what the most existing have been scaled to [31],[6],[26],[9],[7], [32].”
Hierarchical Bayesian Inference and Recursive Regularization for Large-Scale Classification (2015, background): “Although there are a few works that address the scalability of these methods with a large number of training instances [Gornitz et al. 2011; Widmer et al. 2010], there is no work that focuses on scaling with a large number of classes.”
A Survey of Transfer and Multitask Learning in Bioinformatics (2011, background): “[30], who proposed two regularization based multi-task learning methods to predict the splice sites across different organisms.”
Hierarchical Multitask Structured Output Learning for Large-scale Sequence Segmentation (2011, background): “In particular, in computational biology, where evolutionary processes often impose a task hierarchy [22].”
Multitask learning for host–pathogen protein interactions (2013, background): “Because bioinformatics datasets often represent an organism, a natural notion of a ‘task’ is an ‘organ-ism’—for example, the work by Widmer et al. (2010) uses a multitask learning approach for splice-site prediction across many organisms.”
Multi-Task Learning for Dense Prediction Tasks: A Survey (2020, unknown): “nition [32], bioinformatics [33], etc.”