{"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/target-curricula-via-selection-of-minimum","title":"Target Curricula via Selection of Minimum Feature Sets: a Case Study in Boolean Networks","arxiv_id":"1706.04721","date":"2017-06-15","proceeding":null,"authors":["Shannon Fenn","Pablo Moscato"],"abstract":"We consider the effect of introducing a curriculum of targets when training\nBoolean models on supervised Multi Label Classification (MLC) problems. In\nparticular, we consider how to order targets in the absence of prior knowledge,\nand how such a curriculum may be enforced when using meta-heuristics to train\ndiscrete non-linear models.\n  We show that hierarchical dependencies between targets can be exploited by\nenforcing an appropriate curriculum using hierarchical loss functions. On\nseveral multi output circuit-inference problems with known target difficulties,\nFeedforward Boolean Networks (FBNs) trained with such a loss function achieve\nsignificantly lower out-of-sample error, up to $10\\%$ in some cases. This\nimprovement increases as the loss places more emphasis on target order and is\nstrongly correlated with an easy-to-hard curricula. We also demonstrate the\nsame improvements on three real-world models and two Gene Regulatory Network\n(GRN) inference problems.\n  We posit a simple a-priori method for identifying an appropriate target order\nand estimating the strength of target relationships in Boolean MLCs. These\nmethods use intrinsic dimension as a proxy for target difficulty, which is\nestimated using optimal solutions to a combinatorial optimisation problem known\nas the Minimum-Feature-Set (minFS) problem. We also demonstrate that the same\ngeneralisation gains can be achieved without providing any knowledge of target\ndifficulty.","url_abs":"http://arxiv.org/abs/1706.04721v2","url_pdf":"http://arxiv.org/pdf/1706.04721v2.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":"target-curricula-via-selection-of-minimum","repo_url":"https://github.com/shannonfenn/Multi-Label-Curricula-via-Minimum-Feature-Selection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"}],"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}