{"url":"/method/hierarchical-mtl","slug":"hierarchical-mtl","name":"Hierarchical MTL","full_name":"Hierarchical Multi-Task Learning","full_name_withheld":false,"description_markdown":"Multi-task learning (MTL) introduces an inductive bias, based on a-priori relations between tasks: the trainable model is compelled to model more general dependencies by using the abovementioned relation as an important data feature. Hierarchical MTL, in which different tasks use different levels of the deep neural network, provides more effective inductive bias compared to “flat” MTL. Also, hierarchical MTL helps to solve the vanishing gradient problem in deep learning.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Deep multi-task learning with low level tasks supervised at lower layers","paper":"/paper/deep-multi-task-learning-with-low-level-tasks","first_author":"Anders S{\\o}gaard","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deep-multi-task-learning-with-low-level-tasks"},"source":{"url":"https://aclanthology.org/P16-2038","title":"Deep multi-task learning with low level tasks supervised at lower layers","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Deep Tabular Learning","url":"/methods/category/deep-tabular-learning","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":null,"title":"Hierarchical Multi-Task Learning Framework for Session-based Recommendations","date":"2023-09-12","arxiv_id":"2309.06533","n_code_links":0,"syntology":null},{"paper":null,"title":"Provable Pathways: Learning Multiple Tasks over Multiple Paths","date":"2023-03-08","arxiv_id":"2303.04338","n_code_links":0,"syntology":null},{"paper":"/paper/more-layers-end-to-end-regression-and","title":"More layers! End-to-end regression and uncertainty on tabular data with deep learning","date":"2021-12-07","arxiv_id":"2112.03566","n_code_links":1,"syntology":null},{"paper":null,"title":"Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations","date":"2021-10-26","arxiv_id":"2110.13365","n_code_links":0,"syntology":null},{"paper":"/paper/deep-multi-task-learning-with-low-level-tasks","title":"Deep multi-task learning with low level tasks supervised at lower layers","date":"2016-08-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"papers_shown":5,"tasks":[{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":3},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":2},{"task":"/task/ccg-supertagging","name":"CCG Supertagging","papers":1},{"task":"/task/chunking","name":"Chunking","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1},{"task":"/task/generalization-bounds","name":"Generalization Bounds","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/session-based-recommendations","name":"Session-Based Recommendations","papers":1},{"task":"/task/weather-forecasting","name":"Weather Forecasting","papers":1},{"task":"/task/parameter-estimation","name":"parameter estimation","papers":1},{"task":"/task/regression-1","name":"regression","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2016","papers":1},{"year":"2021","papers":2},{"year":"2023","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/hierarchical-mtl"},"syntology_read_at":"2026-09-25T09:33:49+00:00"}