{"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/adaptive-branch-and-bound-tree-exploration","title":"Adaptive Branch-and-Bound Tree Exploration for Neural Network Verification","arxiv_id":"2505.00963","date":"2025-05-02","proceeding":null,"authors":["Kota Fukuda","Guanqin Zhang","Zhenya Zhang","Yulei Sui","Jianjun Zhao"],"abstract":"Formal verification is a rigorous approach that can provably ensure the quality of neural networks, and to date, Branch and Bound (BaB) is the state-of-the-art that performs verification by splitting the problem as needed and applying off-the-shelf verifiers to sub-problems for improved performance. However, existing BaB may not be efficient, due to its naive way of exploring the space of sub-problems that ignores the \\emph{importance} of different sub-problems. To bridge this gap, we first introduce a notion of ``importance'' that reflects how likely a counterexample can be found with a sub-problem, and then we devise a novel verification approach, called ABONN, that explores the sub-problem space of BaB adaptively, in a Monte-Carlo tree search (MCTS) style. The exploration is guided by the ``importance'' of different sub-problems, so it favors the sub-problems that are more likely to find counterexamples. As soon as it finds a counterexample, it can immediately terminate; even though it cannot find, after visiting all the sub-problems, it can still manage to verify the problem. We evaluate ABONN with 552 verification problems from commonly-used datasets and neural network models, and compare it with the state-of-the-art verifiers as baseline approaches. Experimental evaluation shows that ABONN demonstrates speedups of up to $15.2\\times$ on MNIST and $24.7\\times$ on CIFAR-10. We further study the influences of hyperparameters to the performance of ABONN, and the effectiveness of our adaptive tree exploration.","url_abs":"https://arxiv.org/abs/2505.00963v1","url_pdf":"https://arxiv.org/pdf/2505.00963v1.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":"adaptive-branch-and-bound-tree-exploration","repo_url":"https://github.com/DeepLearningVerification/ABONN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"monte-carlo-tree-search","method_name":"Monte-Carlo Tree Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}