{"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/explaining-neural-networks-without-access-to","title":"Explaining Neural Networks without Access to Training Data","arxiv_id":"2206.04891","date":"2022-06-10","proceeding":null,"authors":["Sascha Marton","Stefan Lüdtke","Christian Bartelt","Andrej Tschalzev","Heiner Stuckenschmidt"],"abstract":"We consider generating explanations for neural networks in cases where the network's training data is not accessible, for instance due to privacy or safety issues. Recently, $\\mathcal{I}$-Nets have been proposed as a sample-free approach to post-hoc, global model interpretability that does not require access to training data. They formulate interpretation as a machine learning task that maps network representations (parameters) to a representation of an interpretable function. In this paper, we extend the $\\mathcal{I}$-Net framework to the cases of standard and soft decision trees as surrogate models. We propose a suitable decision tree representation and design of the corresponding $\\mathcal{I}$-Net output layers. Furthermore, we make $\\mathcal{I}$-Nets applicable to real-world tasks by considering more realistic distributions when generating the $\\mathcal{I}$-Net's training data. We empirically evaluate our approach against traditional global, post-hoc interpretability approaches and show that it achieves superior results when the training data is not accessible.","url_abs":"https://arxiv.org/abs/2206.04891v1","url_pdf":"https://arxiv.org/pdf/2206.04891v1.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":"explaining-neural-networks-without-access-to","repo_url":"https://github.com/s-marton/explaining-neural-networks-without-access-to-training-data","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}