{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/label-distribution-learning-forests","title":"Label Distribution Learning Forests","arxiv_id":"1702.06086","date":"2017-02-20","proceeding":"NeurIPS 2017 12","authors":["Wei Shen","Kai Zhao","Yilu Guo","Alan Yuille"],"abstract":"Label distribution learning (LDL) is a general learning framework, which\nassigns to an instance a distribution over a set of labels rather than a single\nlabel or multiple labels. Current LDL methods have either restricted\nassumptions on the expression form of the label distribution or limitations in\nrepresentation learning, e.g., to learn deep features in an end-to-end manner.\nThis paper presents label distribution learning forests (LDLFs) - a novel label\ndistribution learning algorithm based on differentiable decision trees, which\nhave several advantages: 1) Decision trees have the potential to model any\ngeneral form of label distributions by a mixture of leaf node predictions. 2)\nThe learning of differentiable decision trees can be combined with\nrepresentation learning. We define a distribution-based loss function for a\nforest, enabling all the trees to be learned jointly, and show that an update\nfunction for leaf node predictions, which guarantees a strict decrease of the\nloss function, can be derived by variational bounding. The effectiveness of the\nproposed LDLFs is verified on several LDL tasks and a computer vision\napplication, showing significant improvements to the state-of-the-art LDL\nmethods.","url_abs":"http://arxiv.org/abs/1702.06086v4","url_pdf":"http://arxiv.org/pdf/1702.06086v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"age-estimation","task_name":"Age Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-estimation-on-morph-album2-caucasian","task":"Age Estimation","dataset":"MORPH album2 (Caucasian)","model":"dLDLF","rank_in_archive_order":11,"of":11,"metrics":{"MAE":"3.02"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.06086","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}