{"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/tanimoto-random-features-for-scalable-1","title":"Tanimoto Random Features for Scalable Molecular Machine Learning","arxiv_id":"2306.14809","date":"2023-06-26","proceeding":"NeurIPS 2023 11","authors":["Austin Tripp","Sergio Bacallado","Sukriti Singh","José Miguel Hernández-Lobato"],"abstract":"The Tanimoto coefficient is commonly used to measure the similarity between molecules represented as discrete fingerprints, either as a distance metric or a positive definite kernel. While many kernel methods can be accelerated using random feature approximations, at present there is a lack of such approximations for the Tanimoto kernel. In this paper we propose two kinds of novel random features to allow this kernel to scale to large datasets, and in the process discover a novel extension of the kernel to real-valued vectors. We theoretically characterize these random features, and provide error bounds on the spectral norm of the Gram matrix. Experimentally, we show that these random features are effective at approximating the Tanimoto coefficient of real-world datasets and are useful for molecular property prediction and optimization tasks.","url_abs":"https://arxiv.org/abs/2306.14809v2","url_pdf":"https://arxiv.org/pdf/2306.14809v2.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":"tanimoto-random-features-for-scalable-1","repo_url":"https://github.com/austint/tanimoto-random-features-neurips23","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.14809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.14809"}},"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/dockstring/dataset","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/austint/tanimoto-random-features-neurips23","reach":null}],"summary":{"ran":3,"ran_honours":2,"ran_draft_wrong":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":7,"ran":7,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"0d63518d7c7a344e","entry":"PrefactorQMC_Featurizer","repo":"austint/tanimoto-random-features-neurips23","repo_kind":"official","path":"trf23/random_features/tdp.py","file_url":"https://github.com/austint/tanimoto-random-features-neurips23/blob/HEAD/trf23/random_features/tdp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d63518d7c7a344e"}},{"code_sha256_prefix":"1e18577cc272b869","entry":"TDP_PowerSeriesFeaturizer","repo":"austint/tanimoto-random-features-neurips23","repo_kind":"official","path":"trf23/random_features/tdp.py","file_url":"https://github.com/austint/tanimoto-random-features-neurips23/blob/HEAD/trf23/random_features/tdp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e18577cc272b869"}},{"code_sha256_prefix":"d539b7a6bbff315d","entry":"TDP_PowerSeriesTermFeaturizer","repo":"austint/tanimoto-random-features-neurips23","repo_kind":"official","path":"trf23/random_features/tdp.py","file_url":"https://github.com/austint/tanimoto-random-features-neurips23/blob/HEAD/trf23/random_features/tdp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d539b7a6bbff315d"}},{"code_sha256_prefix":"21295215c8d6b0ef","entry":"_draw_gamma_qmc_samples","repo":"austint/tanimoto-random-features-neurips23","repo_kind":"official","path":"trf23/random_features/tdp.py","file_url":"https://github.com/austint/tanimoto-random-features-neurips23/blob/HEAD/trf23/random_features/tdp.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21295215c8d6b0ef"}},{"code_sha256_prefix":"2ec273296b0ab5a7","entry":"_gamma_dist","repo":"austint/tanimoto-random-features-neurips23","repo_kind":"official","path":"trf23/random_features/tdp.py","file_url":"https://github.com/austint/tanimoto-random-features-neurips23/blob/HEAD/trf23/random_features/tdp.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ec273296b0ab5a7"}},{"code_sha256_prefix":"ac2576af5a40ca58","entry":"_tanimoto_power_series_denominator_rf","repo":"austint/tanimoto-random-features-neurips23","repo_kind":"official","path":"trf23/random_features/tdp.py","file_url":"https://github.com/austint/tanimoto-random-features-neurips23/blob/HEAD/trf23/random_features/tdp.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":"ac2576af5a40ca58"}},{"code_sha256_prefix":"ab2270d1ee08d024","entry":"combine_count_sketches","repo":"austint/tanimoto-random-features-neurips23","repo_kind":"official","path":"trf23/random_features/tdp.py","file_url":"https://github.com/austint/tanimoto-random-features-neurips23/blob/HEAD/trf23/random_features/tdp.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab2270d1ee08d024"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}