Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.15469 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912771122135040 |
|---|---|
| author | Kalogeropoulos, Ioannis Bouritsas, Giorgos Panagakis, Yannis |
| author_facet | Kalogeropoulos, Ioannis Bouritsas, Giorgos Panagakis, Yannis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15469 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance Kalogeropoulos, Ioannis Bouritsas, Giorgos Panagakis, Yannis Machine Learning 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. |
| title | Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.15469 |