{"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/calibrating-transformers-via-sparse-gaussian","title":"Calibrating Transformers via Sparse Gaussian Processes","arxiv_id":"2303.02444","date":"2023-03-04","proceeding":null,"authors":["Wenlong Chen","Yingzhen Li"],"abstract":"Transformer models have achieved profound success in prediction tasks in a wide range of applications in natural language processing, speech recognition and computer vision. Extending Transformer's success to safety-critical domains requires calibrated uncertainty estimation which remains under-explored. To address this, we propose Sparse Gaussian Process attention (SGPA), which performs Bayesian inference directly in the output space of multi-head attention blocks (MHAs) in transformer to calibrate its uncertainty. It replaces the scaled dot-product operation with a valid symmetric kernel and uses sparse Gaussian processes (SGP) techniques to approximate the posterior processes of MHA outputs. Empirically, on a suite of prediction tasks on text, images and graphs, SGPA-based Transformers achieve competitive predictive accuracy, while noticeably improving both in-distribution calibration and out-of-distribution robustness and detection.","url_abs":"https://arxiv.org/abs/2303.02444v3","url_pdf":"https://arxiv.org/pdf/2303.02444v3.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":"calibrating-transformers-via-sparse-gaussian","repo_url":"https://github.com/chenw20/sgpa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.02444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02444"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenw20/sgpa","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":5,"samples":[{"code_sha256_prefix":"c8fb662d84660c1b","entry":"return_dataloader","repo":"chenw20/SGPA","repo_kind":"official","path":"train_imdb.py","file_url":"https://github.com/chenw20/SGPA/blob/HEAD/train_imdb.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c8fb662d84660c1b"}},{"code_sha256_prefix":"7d5dbe211af5266a","entry":"scale_dot","repo":"chenw20/sgpa","repo_kind":"official","path":"sgp_layer.py","file_url":"https://github.com/chenw20/sgpa/blob/HEAD/sgp_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d5dbe211af5266a"}},{"code_sha256_prefix":"12c5af6000652052","entry":"SGP_LAYER","repo":"chenw20/sgpa","repo_kind":"official","path":"sgp_layer.py","file_url":"https://github.com/chenw20/sgpa/blob/HEAD/sgp_layer.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":"12c5af6000652052"}},{"code_sha256_prefix":"aea31ab3ac5ccc1d","entry":"kernel_ard","repo":"chenw20/sgpa","repo_kind":"official","path":"sgp_layer.py","file_url":"https://github.com/chenw20/sgpa/blob/HEAD/sgp_layer.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":"aea31ab3ac5ccc1d"}},{"code_sha256_prefix":"5bdabf0f345f186c","entry":"kernel_exp","repo":"chenw20/sgpa","repo_kind":"official","path":"sgp_layer.py","file_url":"https://github.com/chenw20/sgpa/blob/HEAD/sgp_layer.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":"5bdabf0f345f186c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}