{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:13:26Z","timestamp":1768979606203,"version":"3.49.0"},"reference-count":111,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1016\/j.neunet.2025.107507","type":"journal-article","created":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T04:02:52Z","timestamp":1746072172000},"page":"107507","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"special_numbering":"C","title":["On neural architecture search and hyperparameter optimization: A max-flow based approach"],"prefix":"10.1016","volume":"188","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9507-9991","authenticated-orcid":false,"given":"Chao","family":"Xue","sequence":"first","affiliation":[]},{"given":"Jiaxing","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaoxing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yibing","family":"Zhan","sequence":"additional","affiliation":[]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5716-268X","authenticated-orcid":false,"given":"Chun-Guang","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107507_b1","unstructured":"Baker, B., Gupta, O., Naik, N., & Raskar, R. (2017). Designing neural network architectures using reinforcement learning. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b2","unstructured":"Bender, G., Kindermans, P., Zoph, B., Vasudevan, V., & Le, Q. V. (2018). Understanding and Simplifying One-Shot Architecture Search. In International conference on machine learning (pp. 549\u2013558)."},{"key":"10.1016\/j.neunet.2025.107507_b3","first-page":"1","article-title":"GFlowNet foundations","author":"Bengio","year":"2023","journal-title":"The Journal of Machine Learning Research (JMLR)"},{"key":"10.1016\/j.neunet.2025.107507_b4","series-title":"Advances in neural information processing systems","first-page":"27381","article-title":"Flow network based generative models for non-iterative diverse candidate generation","author":"Bengio","year":"2021"},{"key":"10.1016\/j.neunet.2025.107507_b5","series-title":"Advances in neural information processing systems","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","author":"Bergstra","year":"2011"},{"key":"10.1016\/j.neunet.2025.107507_b6","first-page":"281","article-title":"Random search for hyper-parameter optimization","author":"Bergstra","year":"2012","journal-title":"Journal Machine Learning Research (JMLR)"},{"key":"10.1016\/j.neunet.2025.107507_b7","series-title":"Stabilizing darts with amended gradient estimation on architectural parameters","author":"Bi","year":"2019"},{"key":"10.1016\/j.neunet.2025.107507_b8","doi-asserted-by":"crossref","unstructured":"Bochinski, E., Senst, T., & Sikora, T. (2017). Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms. In International conference on image processing (pp. 3924\u20133928).","DOI":"10.1109\/ICIP.2017.8297018"},{"key":"10.1016\/j.neunet.2025.107507_b9","series-title":"Advances in neural information processing systems","first-page":"153","article-title":"Multi-task gaussian process prediction","author":"Bonilla","year":"2008"},{"key":"10.1016\/j.neunet.2025.107507_b10","series-title":"Epistimio\/orion: Asynchronous distributed hyperparameter optimization","author":"Bouthillier","year":"2022"},{"key":"10.1016\/j.neunet.2025.107507_b11","series-title":"Classification and regression trees","author":"Breiman","year":"2017"},{"key":"10.1016\/j.neunet.2025.107507_b12","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.neunet.2023.07.029","article-title":"EPC-DARTS: Efficient partial channel connection for differentiable architecture search","author":"Cai","year":"2023","journal-title":"Neural Networks (NN)"},{"key":"10.1016\/j.neunet.2025.107507_b13","unstructured":"Chen, X., & Hsieh, C.-J. (2020). Stabilizing differentiable architecture search via perturbation-based regularization. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b14","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, L., Wu, J., & Tian, Q. (2019). Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and Evaluation. In International conference on computer vision (pp. 1294\u20131303).","DOI":"10.1109\/ICCV.2019.00138"},{"key":"10.1016\/j.neunet.2025.107507_b15","unstructured":"Chu, X., Wang, X., Zhang, B., Lu, S., Wei, X., & Yan, J. (2021). DARTS-: Robustly Stepping out of Performance Collapse Without Indicators. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b16","unstructured":"Coates, A., Lee, H., & Ng, A. (2011). An analysis of single-layer networks in unsupervised feature learning. In International conference on artificial intelligence and statistics (pp. 215\u2013223)."},{"key":"10.1016\/j.neunet.2025.107507_b17","doi-asserted-by":"crossref","first-page":"5004","DOI":"10.1109\/TNNLS.2021.3067028","article-title":"BNAS: Efficient neural architecture search using broad scalable architecture","author":"Ding","year":"2022","journal-title":"Transactions on Neural Networks and Learning Systems (TNNLS)"},{"key":"10.1016\/j.neunet.2025.107507_b18","doi-asserted-by":"crossref","unstructured":"Dong, X., & Yang, Y. (2019a). One-Shot Neural Architecture Search via Self-Evaluated Template Network. In International conference on computer vision (pp. 3680\u20133689).","DOI":"10.1109\/ICCV.2019.00378"},{"key":"10.1016\/j.neunet.2025.107507_b19","doi-asserted-by":"crossref","unstructured":"Dong, X., & Yang, Y. (2019b). Searching for a Robust Neural Architecture in Four GPU Hours. In Conference on computer vision and pattern recognition (pp. 1761\u20131770).","DOI":"10.1109\/CVPR.2019.00186"},{"key":"10.1016\/j.neunet.2025.107507_b20","unstructured":"Dong, X., & Yang, Y. (2020). NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b21","series-title":"Neural information processing systems track on datasets and benchmarks (NeurIPS datasets and benchmarks)","article-title":"HPOBench: A collection of reproducible multi-fidelity benchmark problems for HPO","author":"Eggensperger","year":"2021"},{"key":"10.1016\/j.neunet.2025.107507_b22","first-page":"1997","article-title":"Neural architecture search: A survey","author":"Elsken","year":"2019","journal-title":"The Journal of Machine Learning Research (JMLR)"},{"key":"10.1016\/j.neunet.2025.107507_b23","series-title":"Advances in neural information processing systems","first-page":"2962","article-title":"Efficient and robust automated machine learning","author":"Feurer","year":"2015"},{"key":"10.1016\/j.neunet.2025.107507_b24","doi-asserted-by":"crossref","unstructured":"Feurer, M., Springenberg, J., & Hutter, F. (2015). Initializing Bayesian Hyperparameter Optimization via Meta-Learning. In Twenty-ninth AAAI conference on artificial intelligence (pp. 1128\u20131135).","DOI":"10.1609\/aaai.v29i1.9354"},{"key":"10.1016\/j.neunet.2025.107507_b25","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1023\/B:MACH.0000027782.67192.13","article-title":"Functional trees","author":"Gama","year":"2004","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2025.107507_b26","series-title":"Caltech-256 object category dataset","author":"Griffin","year":"2007"},{"key":"10.1016\/j.neunet.2025.107507_b27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. In Conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.neunet.2025.107507_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106622","article-title":"AutoML: A survey of the state-of-the-art","author":"He","year":"2021","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2025.107507_b29","doi-asserted-by":"crossref","first-page":"9171","DOI":"10.1109\/TNNLS.2022.3156373","article-title":"PWSNAS: Powering weight sharing NAS with general search space shrinking framework","author":"Hu","year":"2023","journal-title":"Transactions on Neural Networks and Learning Systems (TNNLS)"},{"key":"10.1016\/j.neunet.2025.107507_b30","doi-asserted-by":"crossref","unstructured":"Hutter, F., Hoos, H., & Brown, K. (2011). Sequential model-based optimization for general algorithm configuration. In International conference on learning and intelligent optimization (pp. 507\u2013523).","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"10.1016\/j.neunet.2025.107507_b31","series-title":"Learning and intelligent optimization","first-page":"507","article-title":"Sequential model-based optimization for general algorithm configuration","author":"Hutter","year":"2011"},{"key":"10.1016\/j.neunet.2025.107507_b32","first-page":"52","article-title":"AutoML: A systematic review on automated machine learning with neural architecture search","author":"Imrus","year":"2024","journal-title":"Journal of Information and Intelligence"},{"key":"10.1016\/j.neunet.2025.107507_b33","series-title":"Neural architecture search over a graph search space","author":"Jastrz\u0119bski","year":"2018"},{"key":"10.1016\/j.neunet.2025.107507_b34","unstructured":"Jenatton, R., Archambeau, C., Gonz\u00e1lez, J., & Seeger, M. (2017). Bayesian Optimization with Tree-structured Dependencies. In International conference on machine learning (pp. 1655\u20131664)."},{"key":"10.1016\/j.neunet.2025.107507_b35","series-title":"Advances in neural information processing systems","first-page":"2020","article-title":"Neural architecture search with Bayesian optimisation and optimal transport","author":"Kandasamy","year":"2018"},{"key":"10.1016\/j.neunet.2025.107507_b36","doi-asserted-by":"crossref","unstructured":"Keith, M., Fred, H., Mohammad, S., Rezaei, C., Saeed, S., Linglong, K., et al. (2021). L2nas: Learning to optimize neural architectures via continuous-action reinforcement learning. In Proceedings of the 30th ACM international conference on information and knowledge management (pp. 1284\u20131293).","DOI":"10.1145\/3459637.3482360"},{"key":"10.1016\/j.neunet.2025.107507_b37","series-title":"Tabular benchmarks for joint architecture and hyperparameter optimization","author":"Klein","year":"2019"},{"key":"10.1016\/j.neunet.2025.107507_b38","first-page":"59","article-title":"SampleClean: Fast and reliable analytics on dirty data","author":"Krishnan","year":"2015","journal-title":"IEEE Data Engineering Bulletin"},{"key":"10.1016\/j.neunet.2025.107507_b39","series-title":"Alphaclean: Automatic generation of data cleaning pipelines","author":"Krishnan","year":"2019"},{"key":"10.1016\/j.neunet.2025.107507_b40","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neunet.2025.107507_b41","unstructured":"Li, L., Jamieson, K., & DeSalvo, G. (2017). Hyperband: bandit-based configuration evaluation for hyper-parameter optimization. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b42","first-page":"1","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","author":"Li","year":"2017","journal-title":"Journal Machine Learning Research (JMLR)"},{"key":"10.1016\/j.neunet.2025.107507_b43","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, W., Xue, C., Zhan, Y., Wang, X., Liu, W., et al. (2025). Modeling All Response Surfaces in One for Conditional Search Spaces. In Proceedings of the AAAI conference on artificial intelligence (pp. 1\u20138).","DOI":"10.1609\/aaai.v39i17.34016"},{"key":"10.1016\/j.neunet.2025.107507_b44","doi-asserted-by":"crossref","unstructured":"Li, G., Qian, G., Delgadillo, I. C., Muller, M., Thabet, A., & Ghanem, B. (2020). Sgas: Sequential greedy architecture search. In Conference on computer vision and pattern recognition (pp. 1617\u20131627).","DOI":"10.1109\/CVPR42600.2020.00169"},{"key":"10.1016\/j.neunet.2025.107507_b45","series-title":"Uncertainty in artificial intelligence","first-page":"367","article-title":"Random search and reproducibility for neural architecture search","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2025.107507_b46","first-page":"15195","article-title":"Neural architecture selection as a Nash equilibrium with batch entanglement","author":"Li","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems (TNNLS)"},{"key":"10.1016\/j.neunet.2025.107507_b47","series-title":"Darts+: Improved differentiable architecture search with early stopping","author":"Liang","year":"2019"},{"key":"10.1016\/j.neunet.2025.107507_b48","unstructured":"Liu, H., Simonyan, K., Vinyals, O., Fernando, C., & Kavukcuoglu, K. (2018). Hierarchical Representations for Efficient Architecture Search. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b49","unstructured":"Liu, H., Simonyan, K., & Yang, Y. (2019). DARTS: Differentiable Architecture Search. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b50","doi-asserted-by":"crossref","unstructured":"Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L., et al. (2018). Progressive Neural Architecture Search. In European conference computer vision (pp. 19\u201335).","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"10.1016\/j.neunet.2025.107507_b51","unstructured":"Lizotte, D. J., Wang, T., Bowling, M. H., Schuurmans, D., et al. (2007). Automatic Gait Optimization With Gaussian Process Regression. In International joint conference on artificial intelligence (pp. 944\u2013949)."},{"key":"10.1016\/j.neunet.2025.107507_b52","series-title":"Advances in neural information processing systems","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"10.1016\/j.neunet.2025.107507_b53","series-title":"2017 international joint conference on neural networks","first-page":"364","article-title":"Relational autoencoder for feature extraction","author":"Meng","year":"2017"},{"key":"10.1016\/j.neunet.2025.107507_b54","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2025.107507_b55","first-page":"33269","article-title":"Fruit recognition from images using deep learning","author":"Muresan","year":"2018","journal-title":"Acta Universitatis Sapientiae, Informatica"},{"key":"10.1016\/j.neunet.2025.107507_b56","unstructured":"Nguyen, V., Le, T., Yamada, M., & Osborne, M. A. (2021). Optimal transport kernels for sequential and parallel neural architecture search. In Proceedings of the 38th international conference on machine learning (pp. 8084\u20138095)."},{"key":"10.1016\/j.neunet.2025.107507_b57","doi-asserted-by":"crossref","unstructured":"Nilsback, M.-E., & Zisserman, A. (2008). Automated flower classification over a large number of classes. In Indian conference on computer vision, graphics & image processing (pp. 722\u2013729).","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"10.1016\/j.neunet.2025.107507_b58","series-title":"Feature extraction, construction and selection: A data mining perspective","first-page":"341","article-title":"Constructive induction of cartesian product attributes","author":"Pazzani","year":"1998"},{"key":"10.1016\/j.neunet.2025.107507_b59","series-title":"Advances in neural information processing systems","first-page":"6846","article-title":"Scalable hyperparameter transfer learning","author":"Perrone","year":"2018"},{"key":"10.1016\/j.neunet.2025.107507_b60","unstructured":"Pham, H., Guan, M. Y., Zoph, B., Le, Q. V., & Dean, J. (2018). Efficient Neural Architecture Search via Parameter Sharing. In International conference on machine learning (pp. 4092\u20134101)."},{"key":"10.1016\/j.neunet.2025.107507_b61","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1007\/s00158-013-0919-4","article-title":"A benchmark of kriging-based infill criteria for noisy optimization","author":"Picheny","year":"2013","journal-title":"Structural and Multidisciplinary Optimization"},{"key":"10.1016\/j.neunet.2025.107507_b62","doi-asserted-by":"crossref","DOI":"10.1145\/3643564","article-title":"A survey on AutoML methods and systems for clustering","author":"Poulakis","year":"2024","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"10.1016\/j.neunet.2025.107507_b63","doi-asserted-by":"crossref","unstructured":"Rai, A., Antonova, R., Song, S., Martin, W., Geyer, H., & Atkeson, C. (2018). Bayesian optimization using domain knowledge on the ATRIAS biped. In International conference on robotics and automation (pp. 1771\u20131778).","DOI":"10.1109\/ICRA.2018.8461237"},{"key":"10.1016\/j.neunet.2025.107507_b64","doi-asserted-by":"crossref","unstructured":"Real, E., Aggarwal, A., Huang, Y., & Le, Q. V. (2019). Regularized Evolution for Image Classifier Architecture Search. In The thirty-third AAAI conference on artificial intelligence (pp. 4780\u20134789).","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"10.1016\/j.neunet.2025.107507_b65","unstructured":"Real, E., Moore, S., Selle, A., Saxena, S., Suematsu, Y., Tan, J., et al. (2017). Large-scale evolution of image classifiers. In International conference on machine learning (pp. 2902\u20132911)."},{"key":"10.1016\/j.neunet.2025.107507_b66","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"10.1016\/j.neunet.2025.107507_b67","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.neunet.2023.07.011","article-title":"ATNAS: Automatic termination for neural architecture search","author":"Sakamoto","year":"2023","journal-title":"Neural Networks (NN)"},{"key":"10.1016\/j.neunet.2025.107507_b68","series-title":"Multi-objective differentiable neural architecture search","author":"Sanjay","year":"2024"},{"key":"10.1016\/j.neunet.2025.107507_b69","unstructured":"Shala, G., Elsken, T., Hutter, F., & Grabocka, J. (2023). Transfer NAS with Meta-learned Bayesian Surrogates. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b70","series-title":"Advances in neural information processing systems","first-page":"12486","article-title":"Does unsupervised architecture representation learning help neural architecture search","author":"Shen","year":"2020"},{"key":"10.1016\/j.neunet.2025.107507_b71","series-title":"Advances in neural information processing systems","first-page":"1808","article-title":"Bridging the gap between sample-based and one-shot neural architecture search with BONAS","author":"Shi","year":"2020"},{"key":"10.1016\/j.neunet.2025.107507_b72","unstructured":"Smith, S. L., Kindermans, P., Ying, C., & Le, Q. V. (2018). Don\u2019t Decay the Learning Rate, Increase the Batch Size. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b73","series-title":"Advances in neural information processing systems","first-page":"1257","article-title":"Sparse Gaussian processes using pseudo-inputs","author":"Snelson","year":"2005"},{"key":"10.1016\/j.neunet.2025.107507_b74","series-title":"Advances in neural information processing systems","first-page":"2960","article-title":"Practical bayesian optimization of machine learning algorithms","author":"Snoek","year":"2012"},{"key":"10.1016\/j.neunet.2025.107507_b75","series-title":"Advances in neural information processing systems","first-page":"4134","article-title":"Bayesian optimization with robust Bayesian neural networks","author":"Springenberg","year":"2016"},{"key":"10.1016\/j.neunet.2025.107507_b76","unstructured":"Srinivas, N., Krause, A., Kakade, S. M., & Seeger, M. W. (2010). Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design. In International conference on machine learning (pp. 1015\u20131022)."},{"key":"10.1016\/j.neunet.2025.107507_b77","doi-asserted-by":"crossref","unstructured":"Stang, M., Meier, C., Rau, V., & Sax, E. (2019). An Evolutionary Approach to Hyper-Parameter Optimization of Neural Networks. In International conference on human interaction and emerging technologies (pp. 713\u2013718).","DOI":"10.1007\/978-3-030-25629-6_111"},{"key":"10.1016\/j.neunet.2025.107507_b78","doi-asserted-by":"crossref","unstructured":"Su, X., Huang, T., Li, Y., You, S., Wang, F., Qian, C., et al. (2021). Prioritized architecture sampling with monto-carlo tree search. In Conference on computer vision and pattern recognition (pp. 10968\u201310977).","DOI":"10.1109\/CVPR46437.2021.01082"},{"key":"10.1016\/j.neunet.2025.107507_b79","unstructured":"Sui, Y., Gotovos, A., Burdick, J., & Krause, A. (2015). Safe exploration for optimization with Gaussian processes. In International conference on machine learning (pp. 997\u20131005)."},{"key":"10.1016\/j.neunet.2025.107507_b80","series-title":"Advances in neural information processing systems","first-page":"2004","article-title":"Multi-task bayesian optimization","author":"Swersky","year":"2013"},{"key":"10.1016\/j.neunet.2025.107507_b81","unstructured":"Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In International conference on machine learning (pp. 6105\u20136114)."},{"key":"10.1016\/j.neunet.2025.107507_b82","series-title":"Data classification: Algorithms and applications","first-page":"37","article-title":"Feature selection for classification: A review","author":"Tang","year":"2014"},{"key":"10.1016\/j.neunet.2025.107507_b83","doi-asserted-by":"crossref","unstructured":"Umair, N., Sam, E., Julian, T., Steven, J., & Christopher, C. (2024). LLMatic: neural architecture search via large language models and quality diversity optimization. In Proceedings of the genetic and evolutionary computation conference (pp. 1110\u20131118).","DOI":"10.1145\/3638529.3654017"},{"key":"10.1016\/j.neunet.2025.107507_b84","series-title":"Feature extraction, construction and selection: A data mining perspective","first-page":"307","article-title":"Evolutionary feature space transformation","author":"Vafaie","year":"1998"},{"key":"10.1016\/j.neunet.2025.107507_b85","series-title":"Special interest group on knowledge discovery and data mining","first-page":"49","article-title":"OpenML: Networked science in machine learning","author":"Vanschoren","year":"2013"},{"key":"10.1016\/j.neunet.2025.107507_b86","unstructured":"Wang, R., Cheng, M., Chen, X., Tang, X., & Hsieh, C. J. (2021). Rethinking Architecture Selection in Differentiable NAS. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b87","series-title":"Advances in neural information processing systems","first-page":"180","article-title":"Learning search space partition for black-box optimization using monte carlo tree search","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2025.107507_b88","series-title":"Advances in neural information processing systems","first-page":"12868","article-title":"ZARTS: On zero-order optimization for neural architecture search","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2025.107507_b89","unstructured":"Wang, X., Li, J., Xue, C., Liu, W., Liu, W., Yang, X., et al. (2023). Poisson Process for Bayesian Optimization. In International conference on automated machine learning (pp. 1\u201320)."},{"key":"10.1016\/j.neunet.2025.107507_b90","doi-asserted-by":"crossref","unstructured":"Wang, X., Xue, C., Yan, J., Yang, X., Hu, Y., & Sun, K. (2020). MergeNAS: Merge Operations into One for Differentiable Architecture Search. In International joint conference on artificial intelligence (pp. 3065\u20133072).","DOI":"10.24963\/ijcai.2020\/424"},{"key":"10.1016\/j.neunet.2025.107507_b91","doi-asserted-by":"crossref","first-page":"8441","DOI":"10.1109\/TNNLS.2022.3151160","article-title":"NPENAS: Neural predictor guided evolution for neural architecture search","author":"Wei","year":"2023","journal-title":"Transactions on Neural Networks and Learning Systems (TNNLS)"},{"key":"10.1016\/j.neunet.2025.107507_b92","series-title":"Introduction to graph theory","author":"West","year":"1996"},{"key":"10.1016\/j.neunet.2025.107507_b93","doi-asserted-by":"crossref","unstructured":"White, C., Neiswanger, W., & Savani, Y. (2021). BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search. In Thirty-fifth AAAI conference on artificial intelligence (pp. 10293\u201310301).","DOI":"10.1609\/aaai.v35i12.17233"},{"key":"10.1016\/j.neunet.2025.107507_b94","unstructured":"Wistuba, M., & Grabocka, J. (2021). Few-Shot Bayesian Optimization with Deep Kernel Surrogates. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b95","doi-asserted-by":"crossref","unstructured":"Xie, S., Kirillov, A., Girshick, R. B., & He, K. (2019). Exploring Randomly Wired Neural Networks for Image Recognition. In International conference on computer vision (pp. 1284\u20131293).","DOI":"10.1109\/ICCV.2019.00137"},{"key":"10.1016\/j.neunet.2025.107507_b96","doi-asserted-by":"crossref","unstructured":"Xie, L., & Yuille, A. L. (2017). Genetic CNN. In IEEE international conference on computer vision (pp. 1388\u20131397).","DOI":"10.1109\/ICCV.2017.154"},{"key":"10.1016\/j.neunet.2025.107507_b97","unstructured":"Xie, S., Zheng, H., Liu, C., & Lin, L. (2019). SNAS: stochastic neural architecture search. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b98","unstructured":"Xu, Y., Xie, L., Zhang, X., Chen, X., Qi, G.-J., Tian, Q., et al. (2019). PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b99","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108474","article-title":"Automated search space and search strategy selection for AutoML","author":"Xue","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.107507_b100","doi-asserted-by":"crossref","unstructured":"Xue, C., Wang, X., Yan, J., Hu, Y., Yang, X., & Sun, K. (2021). Rethinking Bi-Level Optimization in Neural Architecture Search: A Gibbs Sampling Perspective. In Thirty-fifth AAAI conference on artificial intelligence (pp. 10551\u201310559).","DOI":"10.1609\/aaai.v35i12.17262"},{"key":"10.1016\/j.neunet.2025.107507_b101","doi-asserted-by":"crossref","unstructured":"Xue, C., Wang, X., Yan, J., & Li, C. (2022). A Max-Flow Based Approach for Neural Architecture Search. In European conference computer vision (pp. 685\u2013701).","DOI":"10.1007\/978-3-031-20044-1_39"},{"key":"10.1016\/j.neunet.2025.107507_b102","doi-asserted-by":"crossref","unstructured":"Xue, C., Yan, J., Yan, R., Chu, S. M., Hu, Y., & Lin, Y. (2019). Transferable AutoML by Model Sharing Over Grouped Datasets. In IEEE conference on computer vision and pattern recognition (pp. 9002\u20139011).","DOI":"10.1109\/CVPR.2019.00921"},{"key":"10.1016\/j.neunet.2025.107507_b103","doi-asserted-by":"crossref","first-page":"4861","DOI":"10.1109\/TNNLS.2021.3061630","article-title":"A gradient-guided evolutionary approach to training deep neural networks","author":"Yang","year":"2022","journal-title":"Transactions on Neural Networks and Learning Systems (TNNLS)"},{"key":"10.1016\/j.neunet.2025.107507_b104","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, Y., Chen, X., Shi, B., Xu, C., Xu, C., et al. (2020). CARS: Continuous Evolution for Efficient Neural Architecture Search. In Conference on computer vision and pattern recognition (pp. 1826\u20131835).","DOI":"10.1109\/CVPR42600.2020.00190"},{"key":"10.1016\/j.neunet.2025.107507_b105","series-title":"Hyper-parameter optimization: A review of algorithms and applications","author":"Yu","year":"2020"},{"key":"10.1016\/j.neunet.2025.107507_b106","unstructured":"Zela, A., Elsken, T., Saikia, T., Marrakchi, Y., Brox, T., & Hutter, F. (2020). Understanding and Robustifying Differentiable Architecture Search. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b107","unstructured":"Zhang, S., Jia, F., Wang, C., & Wu, Q. (2023). Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b108","unstructured":"Zhou, H., Yang, M., Wang, J., & Pan, W. (2019). BayesNAS: A Bayesian Approach for Neural Architecture Search. In International conference on machine learning (pp. 7603\u20137613)."},{"key":"10.1016\/j.neunet.2025.107507_b109","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1016\/j.neunet.2023.08.062","article-title":"Improving differentiable architecture search via self-distillation","author":"Zhu","year":"2023","journal-title":"Neural Networks (NN)"},{"key":"10.1016\/j.neunet.2025.107507_b110","unstructured":"Zoph, B., & Le, Q. (2017). Neural architecture search with reinforcement learning. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107507_b111","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018). Learning Transferable Architectures for Scalable Image Recognition. In Conference on computer vision and pattern recognition (pp. 8697\u20138710).","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025003867?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025003867?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T02:36:40Z","timestamp":1748313400000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025003867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":111,"alternative-id":["S0893608025003867"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107507","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"On neural architecture search and hyperparameter optimization: A max-flow based approach","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107507","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107507"}}