{"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/rethinking-the-principle-of-gradient-smooth","title":"Rethinking the Principle of Gradient Smooth Methods in Model Explanation","arxiv_id":"2410.07711","date":"2024-10-10","proceeding":null,"authors":["Linjiang Zhou","Chao Ma","Zepeng Wang","Xiaochuan Shi"],"abstract":"Gradient Smoothing is an efficient approach to reducing noise in gradient-based model explanation method. SmoothGrad adds Gaussian noise to mitigate much of these noise. However, the crucial hyper-parameter in this method, the variance $\\sigma$ of Gaussian noise, is set manually or with heuristic approach. However, it results in the smoothed gradients still containing a certain amount of noise. In this paper, we aim to interpret SmoothGrad as a corollary of convolution, thereby re-understanding the gradient noise and the role of $\\sigma$ from the perspective of confidence level. Furthermore, we propose an adaptive gradient smoothing method, AdaptGrad, based on these insights. Through comprehensive experiments, both qualitative and quantitative results demonstrate that AdaptGrad could effectively reduce almost all the noise in vanilla gradients compared with baselines methods. AdaptGrad is simple and universal, making it applicable for enhancing gradient-based interpretability methods for better visualization.","url_abs":"https://arxiv.org/abs/2410.07711v1","url_pdf":"https://arxiv.org/pdf/2410.07711v1.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":[],"tasks":[],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.07711","atlas_url":"https://app.syntology.ai/?focus=2410.07711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07711"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/AiShare-WHU/AdaptGrad","reach":null}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":4,"ran":1,"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":"dfb26ad8f225fa05","entry":"AdaptedGaussianSigma","repo":"AiShare-WHU/AdaptGrad","repo_kind":"found_in_text","path":"saliency.py","file_url":"https://github.com/AiShare-WHU/AdaptGrad/blob/HEAD/saliency.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":"dfb26ad8f225fa05"}},{"code_sha256_prefix":"ce2e4950967fd9b1","entry":"Bound","repo":"AiShare-WHU/AdaptGrad","repo_kind":"found_in_text","path":"saliency.py","file_url":"https://github.com/AiShare-WHU/AdaptGrad/blob/HEAD/saliency.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":"ce2e4950967fd9b1"}},{"code_sha256_prefix":"e0c0ea2a236d625e","entry":"GPU","repo":"AiShare-WHU/AdaptGrad","repo_kind":"found_in_text","path":"saliency.py","file_url":"https://github.com/AiShare-WHU/AdaptGrad/blob/HEAD/saliency.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":"e0c0ea2a236d625e"}},{"code_sha256_prefix":"7893755c589855af","entry":"Sigma","repo":"AiShare-WHU/AdaptGrad","repo_kind":"found_in_text","path":"saliency.py","file_url":"https://github.com/AiShare-WHU/AdaptGrad/blob/HEAD/saliency.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":"7893755c589855af"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}