{"ID":2828061,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.15469","arxiv_id":"2512.15469","title":"Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance","abstract":"As machine learning models are increasingly deployed in high-stakes settings, e.g. as decision support systems in various societal sectors or in critical infrastructure, designers and auditors are facing the need to ensure that models satisfy a wider variety of requirements (e.g. compliance with regulations, fairness, computational constraints) beyond performance. Although most of them are the subject of ongoing studies, typical approaches face critical challenges: post-processing methods tend to compromise performance, which is often counteracted by fine-tuning or, worse, training from scratch, an often time-consuming or even unavailable strategy. This raises the following question: \"Can we efficiently edit models to satisfy requirements, without sacrificing their utility?\" In this work, we approach this with a unifying framework, in a data-driven manner, i.e. we learn to edit neural networks (NNs), where the editor is an NN itself - a graph metanetwork - and editing amounts to a single inference step. In particular, the metanetwork is trained on NN populations to minimise an objective consisting of two terms: the requirement to be enforced and the preservation of the NN's utility. We experiment with diverse tasks (the data minimisation principle, bias mitigation and weight pruning) improving the trade-offs between performance, requirement satisfaction and time efficiency compared to popular post-processing or re-training alternatives.","short_abstract":"As machine learning models are increasingly deployed in high-stakes settings, e.g. as decision support systems in various societal sectors or in critical infrastructure, designers and auditors are facing the need to ensure that models satisfy a wider variety of requirements (e.g. compliance with regulations, fairness,...","url_abs":"https://arxiv.org/abs/2512.15469","url_pdf":"https://arxiv.org/pdf/2512.15469v1","authors":"[\"Ioannis Kalogeropoulos\",\"Giorgos Bouritsas\",\"Yannis Panagakis\"]","published":"2025-12-17T14:13:19Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}