{"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/feature-space-particle-inference-for-neural","title":"Feature Space Particle Inference for Neural Network Ensembles","arxiv_id":"2206.00944","date":"2022-06-02","proceeding":null,"authors":["Shingo Yashima","Teppei Suzuki","Kohta Ishikawa","Ikuro Sato","Rei Kawakami"],"abstract":"Ensembles of deep neural networks demonstrate improved performance over single models. For enhancing the diversity of ensemble members while keeping their performance, particle-based inference methods offer a promising approach from a Bayesian perspective. However, the best way to apply these methods to neural networks is still unclear: seeking samples from the weight-space posterior suffers from inefficiency due to the over-parameterization issues, while seeking samples directly from the function-space posterior often results in serious underfitting. In this study, we propose optimizing particles in the feature space where the activation of a specific intermediate layer lies to address the above-mentioned difficulties. Our method encourages each member to capture distinct features, which is expected to improve ensemble prediction robustness. Extensive evaluation on real-world datasets shows that our model significantly outperforms the gold-standard Deep Ensembles on various metrics, including accuracy, calibration, and robustness. Code is available at https://github.com/DensoITLab/featurePI .","url_abs":"https://arxiv.org/abs/2206.00944v1","url_pdf":"https://arxiv.org/pdf/2206.00944v1.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":"feature-space-particle-inference-for-neural","repo_url":"https://github.com/densoitlab/featurepi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[{"method_slug":"deep-ensembles","method_name":"Deep Ensembles"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.00944","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}