{"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/granger-causal-attentive-mixtures-of-experts","title":"Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks","arxiv_id":"1802.02195","date":"2018-02-06","proceeding":null,"authors":["Patrick Schwab","Djordje Miladinovic","Walter Karlen"],"abstract":"Knowledge of the importance of input features towards decisions made by\nmachine-learning models is essential to increase our understanding of both the\nmodels and the underlying data. Here, we present a new approach to estimating\nfeature importance with neural networks based on the idea of distributing the\nfeatures of interest among experts in an attentive mixture of experts (AME).\nAMEs use attentive gating networks trained with a Granger-causal objective to\nlearn to jointly produce accurate predictions as well as estimates of feature\nimportance in a single model. Our experiments show (i) that the feature\nimportance estimates provided by AMEs compare favourably to those provided by\nstate-of-the-art methods, (ii) that AMEs are significantly faster at estimating\nfeature importance than existing methods, and (iii) that the associations\ndiscovered by AMEs are consistent with those reported by domain experts.","url_abs":"http://arxiv.org/abs/1802.02195v6","url_pdf":"http://arxiv.org/pdf/1802.02195v6.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":[{"paper_slug":"granger-causal-attentive-mixtures-of-experts","repo_url":"https://github.com/d909b/ame","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}