[{"publication_status":"published","oa_version":"None","department":[{"_id":"FrLo"}],"alternative_title":["Advances in Neural Information Processing Systems"],"scopus_import":"1","researchdata_availability":"yes","type":"conference","acknowledgement":"We thank Gregor Krzmanc, German Magai, Vital Fernandez for insightful discussions in the early\r\nstages of the project. HY was supported by the Research Council of Finland Flagship programme:\r\nFinnish Center for Artificial Intelligence FCAI. HY wishes to acknowledge CSC - IT Center for\r\nScience, Finland, for computational resources. GA was supported by the DFF Sapere Aude Starting\r\nGrant “GADL”. SH was supported by a research grant (42062) from VILLUM FONDEN and partly\r\nfunded by the Novo Nordisk Foundation through the Center for Basic Research in Life Science\r\n(NNF20OC0062606). SH received funding from the European Research Council (ERC) under the\r\nEuropean Union’s Horizon Programme (grant agreement 101125003). MF is supported by the MSCA\r\nIST-Bridge fellowship which has received funding from the European Union’s Horizon 2020 research\r\nand innovation program under the Marie Skłodowska-Curie grant agreement No 101034413.","citation":{"short":"H. Yu, B. Inal, G. Arvanitidis, S. Hauberg, F. Locatello, M. Fumero, in:, 39th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025, pp. 125316–125360.","mla":"Yu, Hanlin, et al. “Connecting Neural Models Latent Geometries with Relative Geodesic Representations.” <i>39th Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025, pp. 125316–60, doi:<a href=\"https://doi.org/10.52202/085713-3769\">10.52202/085713-3769</a>.","apa":"Yu, H., Inal, B., Arvanitidis, G., Hauberg, S., Locatello, F., &#38; Fumero, M. (2025). Connecting neural models latent geometries with relative geodesic representations. In <i>39th Conference on Neural Information Processing Systems</i> (Vol. 38, pp. 125316–125360). San Diego, CA, United States: Neural Information Processing Systems Foundation. <a href=\"https://doi.org/10.52202/085713-3769\">https://doi.org/10.52202/085713-3769</a>","chicago":"Yu, Hanlin, Berfin Inal, Georgios Arvanitidis, Søren Hauberg, Francesco Locatello, and Marco Fumero. “Connecting Neural Models Latent Geometries with Relative Geodesic Representations.” In <i>39th Conference on Neural Information Processing Systems</i>, 38:125316–60. Neural Information Processing Systems Foundation, 2025. <a href=\"https://doi.org/10.52202/085713-3769\">https://doi.org/10.52202/085713-3769</a>.","ama":"Yu H, Inal B, Arvanitidis G, Hauberg S, Locatello F, Fumero M. Connecting neural models latent geometries with relative geodesic representations. In: <i>39th Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025:125316-125360. doi:<a href=\"https://doi.org/10.52202/085713-3769\">10.52202/085713-3769</a>","ista":"Yu H, Inal B, Arvanitidis G, Hauberg S, Locatello F, Fumero M. 2025. Connecting neural models latent geometries with relative geodesic representations. 39th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38, 125316–125360.","ieee":"H. Yu, B. Inal, G. Arvanitidis, S. Hauberg, F. Locatello, and M. Fumero, “Connecting neural models latent geometries with relative geodesic representations,” in <i>39th Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38, pp. 125316–125360."},"volume":38,"related_material":{"link":[{"relation":"software","url":" https://github.com/marc0git/RelativeGeodesics"}]},"corr_author":"1","doi":"10.52202/085713-3769","year":"2025","author":[{"full_name":"Yu, Hanlin","last_name":"Yu","first_name":"Hanlin"},{"last_name":"Inal","first_name":"Berfin","full_name":"Inal, Berfin"},{"first_name":"Georgios","last_name":"Arvanitidis","full_name":"Arvanitidis, Georgios"},{"full_name":"Hauberg, Søren","first_name":"Søren","last_name":"Hauberg"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","last_name":"Locatello","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco"},{"full_name":"Fumero, Marco","last_name":"Fumero","first_name":"Marco","id":"1c1593eb-393f-11ef-bb8e-ab4f1e979650"}],"page":"125316-125360","publication_identifier":{"eissn":["1049-5258"],"isbn":["9798331338275"]},"project":[{"call_identifier":"H2020","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c","name":"IST-BRIDGE: International postdoctoral program","grant_number":"101034413"}],"das_tickbox":"0","external_id":{"arxiv":["2506.01599"]},"publication":"39th Conference on Neural Information Processing Systems","date_published":"2025-12-01T00:00:00Z","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"Neural models learn representations of high-dimensional data on low-dimensional\r\nmanifolds. Multiple factors, including stochasticities in the training process, model\r\narchitectures, and additional inductive biases, may induce different representations,\r\neven when learning the same task on the same data. However, it has recently been\r\nshown that when a latent structure is shared between distinct latent spaces, relative\r\ndistances between representations can be preserved, up to distortions. Building\r\non this idea, we demonstrate that exploiting the differential-geometric structure of\r\nlatent spaces of neural models, it is possible to capture precisely the transformations\r\nbetween representational spaces trained on similar data distributions. Specifically,\r\nwe assume that distinct neural models parametrize approximately the same underlying manifold, and introduce a representation based on the pullback metric\r\nthat captures the intrinsic structure of the latent space, while scaling efficiently\r\nto large models. We validate experimentally our method on model stitching and\r\nretrieval tasks, covering autoencoders and vision foundation discriminative models,\r\nacross diverse architectures, datasets, pretraining schemes and modalities. Code is\r\navailable at https://github.com/marc0git/RelativeGeodesics."}],"quality_controlled":"1","status":"public","ec_funded":1,"day":"01","conference":{"end_date":"2025-12-07","location":"San Diego, CA, United States","name":"NeurIPS: Neural Information Processing Systems","start_date":"2025-12-02"},"title":"Connecting neural models latent geometries with relative geodesic representations","intvolume":"        38","arxiv":1,"date_created":"2026-09-06T22:02:01Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_updated":"2026-09-17T07:09:28Z","supplementarymaterial":"yes","_id":"22831","article_processing_charge":"No","fulldoi":"https://doi.org/10.52202/085713-3769","month":"12","publisher":"Neural Information Processing Systems Foundation"}]