{"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/shifting-the-paradigm-a-diffeomorphism","title":"Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning","arxiv_id":"2502.19921","date":"2025-02-27","proceeding":null,"authors":["Berken Utku Demirel","Christian Holz"],"abstract":"Deep learning models lack shift invariance, making them sensitive to input shifts that cause changes in output. While recent techniques seek to address this for images, our findings show that these approaches fail to provide shift-invariance in time series, where the data generation mechanism is more challenging due to the interaction of low and high frequencies. Worse, they also decrease performance across several tasks. In this paper, we propose a novel differentiable bijective function that maps samples from their high-dimensional data manifold to another manifold of the same dimension, without any dimensional reduction. Our approach guarantees that samples -- when subjected to random shifts -- are mapped to a unique point in the manifold while preserving all task-relevant information without loss. We theoretically and empirically demonstrate that the proposed transformation guarantees shift-invariance in deep learning models without imposing any limits to the shift. Our experiments on six time series tasks with state-of-the-art methods show that our approach consistently improves the performance while enabling models to achieve complete shift-invariance without modifying or imposing restrictions on the model's topology. The source code is available on \\href{https://github.com/eth-siplab/Shifting-the-Paradigm}{GitHub}.","url_abs":"https://arxiv.org/abs/2502.19921v1","url_pdf":"https://arxiv.org/pdf/2502.19921v1.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":"shifting-the-paradigm-a-diffeomorphism","repo_url":"https://github.com/eth-siplab/shifting-the-paradigm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.19921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19921"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/dwromero/wavelet_networks","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/arnab39/equiadapt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eth-siplab/shifting-the-paradigm","reach":null}],"summary":{"ran":2,"ran_fixture":2,"unverified":10},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"found_in_text":{"samples":13,"ran":4,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"0c1a3b38fa136c12","entry":"BaseCanonicalization","repo":"arnab39/equiadapt","repo_kind":"found_in_text","path":"equiadapt/images/canonicalization/continuous_group.py","file_url":"https://github.com/arnab39/equiadapt/blob/HEAD/equiadapt/images/canonicalization/continuous_group.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c1a3b38fa136c12"}},{"code_sha256_prefix":"87001b711bf5fffa","entry":"ContinuousGroupCanonicalization","repo":"arnab39/equiadapt","repo_kind":"found_in_text","path":"equiadapt/images/canonicalization/continuous_group.py","file_url":"https://github.com/arnab39/equiadapt/blob/HEAD/equiadapt/images/canonicalization/continuous_group.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"87001b711bf5fffa"}},{"code_sha256_prefix":"9d593992f15b436d","entry":"gram_schmidt","repo":"arnab39/equiadapt","repo_kind":"found_in_text","path":"equiadapt/images/canonicalization/continuous_group.py","file_url":"https://github.com/arnab39/equiadapt/blob/HEAD/equiadapt/images/canonicalization/continuous_group.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d593992f15b436d"}},{"code_sha256_prefix":"474b10f0d6fc6999","entry":"roll_by_gather","repo":"arnab39/equiadapt","repo_kind":"found_in_text","path":"equiadapt/images/canonicalization/continuous_group.py","file_url":"https://github.com/arnab39/equiadapt/blob/HEAD/equiadapt/images/canonicalization/continuous_group.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"474b10f0d6fc6999"}},{"code_sha256_prefix":"aa37b630a8115416","entry":"B","repo":"eth-siplab/shifting-the-paradigm","repo_kind":"official","path":"eerie/bsplines/b_1d.py","file_url":"https://github.com/eth-siplab/shifting-the-paradigm/blob/HEAD/eerie/bsplines/b_1d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa37b630a8115416"}},{"code_sha256_prefix":"831e6bd395edea27","entry":"B_supp","repo":"dwromero/wavelet_networks","repo_kind":"found_in_text","path":"eerie/bsplines/b_1d.py","file_url":"https://github.com/dwromero/wavelet_networks/blob/HEAD/eerie/bsplines/b_1d.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"831e6bd395edea27"}},{"code_sha256_prefix":"de2f1fa0496f8c87","entry":"B_supp_grid","repo":"dwromero/wavelet_networks","repo_kind":"found_in_text","path":"eerie/bsplines/b_1d.py","file_url":"https://github.com/dwromero/wavelet_networks/blob/HEAD/eerie/bsplines/b_1d.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de2f1fa0496f8c87"}},{"code_sha256_prefix":"55b807958e61e16c","entry":"B_supp_grid","repo":"dwromero/wavelet_networks","repo_kind":"found_in_text","path":"eerie/bsplines/utils.py","file_url":"https://github.com/dwromero/wavelet_networks/blob/HEAD/eerie/bsplines/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55b807958e61e16c"}},{"code_sha256_prefix":"27a6d19f3a4316e0","entry":"B_supp_grid_2","repo":"dwromero/wavelet_networks","repo_kind":"found_in_text","path":"eerie/bsplines/utils.py","file_url":"https://github.com/dwromero/wavelet_networks/blob/HEAD/eerie/bsplines/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27a6d19f3a4316e0"}},{"code_sha256_prefix":"3c6ae537a3cfa74a","entry":"ContinuousGroupImageCanonicalization","repo":"arnab39/equiadapt","repo_kind":"found_in_text","path":"equiadapt/images/canonicalization/continuous_group.py","file_url":"https://github.com/arnab39/equiadapt/blob/HEAD/equiadapt/images/canonicalization/continuous_group.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c6ae537a3cfa74a"}},{"code_sha256_prefix":"af49bc7f7009b05b","entry":"get_action_on_image_features","repo":"arnab39/equiadapt","repo_kind":"found_in_text","path":"equiadapt/images/canonicalization/continuous_group.py","file_url":"https://github.com/arnab39/equiadapt/blob/HEAD/equiadapt/images/canonicalization/continuous_group.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"af49bc7f7009b05b"}},{"code_sha256_prefix":"76eb63161c2aab4a","entry":"weights_init","repo":"dwromero/wavelet_networks","repo_kind":"found_in_text","path":"eerie/nn/conv.py","file_url":"https://github.com/dwromero/wavelet_networks/blob/HEAD/eerie/nn/conv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76eb63161c2aab4a"}},{"code_sha256_prefix":"09c43ae48e1f7930","entry":"x_centers_init","repo":"dwromero/wavelet_networks","repo_kind":"found_in_text","path":"eerie/nn/conv.py","file_url":"https://github.com/dwromero/wavelet_networks/blob/HEAD/eerie/nn/conv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09c43ae48e1f7930"}},{"code_sha256_prefix":"94ce42935f0bfe49","entry":"x_h_centers_init","repo":"dwromero/wavelet_networks","repo_kind":"found_in_text","path":"eerie/nn/conv.py","file_url":"https://github.com/dwromero/wavelet_networks/blob/HEAD/eerie/nn/conv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94ce42935f0bfe49"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}