{"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/revisiting-essential-and-nonessential","title":"Revisiting Essential and Nonessential Settings of Evidential Deep Learning","arxiv_id":"2410.00393","date":"2024-10-01","proceeding":null,"authors":["Mengyuan Chen","Junyu Gao","Changsheng Xu"],"abstract":"Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that provides reliable predictive uncertainty in a single forward pass, attracting significant attention. Grounded in subjective logic, EDL derives Dirichlet concentration parameters from neural networks to construct a Dirichlet probability density function (PDF), modeling the distribution of class probabilities. Despite its success, EDL incorporates several nonessential settings: In model construction, (1) a commonly ignored prior weight parameter is fixed to the number of classes, while its value actually impacts the balance between the proportion of evidence and its magnitude in deriving predictive scores. In model optimization, (2) the empirical risk features a variance-minimizing optimization term that biases the PDF towards a Dirac delta function, potentially exacerbating overconfidence. (3) Additionally, the structural risk typically includes a KL-divergence-minimizing regularization, whose optimization direction extends beyond the intended purpose and contradicts common sense, diminishing the information carried by the evidence magnitude. Therefore, we propose Re-EDL, a simplified yet more effective variant of EDL, by relaxing the nonessential settings and retaining the essential one, namely, the adoption of projected probability from subjective logic. Specifically, Re-EDL treats the prior weight as an adjustable hyperparameter rather than a fixed scalar, and directly optimizes the expectation of the Dirichlet PDF provided by deprecating both the variance-minimizing optimization term and the divergence regularization term. Extensive experiments and state-of-the-art performance validate the effectiveness of our method. The source code is available at https://github.com/MengyuanChen21/Re-EDL.","url_abs":"https://arxiv.org/abs/2410.00393v1","url_pdf":"https://arxiv.org/pdf/2410.00393v1.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":"revisiting-essential-and-nonessential","repo_url":"https://github.com/mengyuanchen21/re-edl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"model-optimization","task_name":"Model Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.00393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00393"}},"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/mengyuanchen21/re-edl","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":9,"samples":[{"code_sha256_prefix":"97c4dc7fc640a2e9","entry":"accuracy","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_fsl/metrics.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_fsl/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"97c4dc7fc640a2e9"}},{"code_sha256_prefix":"53ebd0b432c5eaf0","entry":"alexnet","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_classical/architectures/alexnet_sequential.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_classical/architectures/alexnet_sequential.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53ebd0b432c5eaf0"}},{"code_sha256_prefix":"a27310bc46a19912","entry":"brier_score","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_fsl/metrics.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_fsl/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a27310bc46a19912"}},{"code_sha256_prefix":"24ef5133c979df88","entry":"compute_output","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_fsl/evaluation.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_fsl/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24ef5133c979df88"}},{"code_sha256_prefix":"12ae37b538027ed7","entry":"compute_output","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_fsl/our_evaluation.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_fsl/our_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"12ae37b538027ed7"}},{"code_sha256_prefix":"8091430f67780266","entry":"resnet18","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_classical/architectures/resnet_sequential.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_classical/architectures/resnet_sequential.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8091430f67780266"}},{"code_sha256_prefix":"e7368c4266d2b6e0","entry":"confidence","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_fsl/metrics.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_fsl/metrics.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":"e7368c4266d2b6e0"}},{"code_sha256_prefix":"a08eba5fbc8e46bb","entry":"get_dataset","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_classical/dataset.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_classical/dataset.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":"a08eba5fbc8e46bb"}},{"code_sha256_prefix":"d5058ce0b8ea2a89","entry":"get_dataset_info","repo":"mengyuanchen21/re-edl","repo_kind":"official","path":"code_classical/dataset.py","file_url":"https://github.com/mengyuanchen21/re-edl/blob/HEAD/code_classical/dataset.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":"d5058ce0b8ea2a89"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}