{"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/robust-fine-tuning-of-deep-neural-networks","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","arxiv_id":"2206.02659","date":"2022-06-06","proceeding":null,"authors":["Haotian Ju","Dongyue Li","Hongyang R. Zhang"],"abstract":"We consider fine-tuning a pretrained deep neural network on a target task. We study the generalization properties of fine-tuning to understand the problem of overfitting, which has often been observed (e.g., when the target dataset is small or when the training labels are noisy). Existing generalization measures for deep networks depend on notions such as distance from the initialization (i.e., the pretrained network) of the fine-tuned model and noise stability properties of deep networks. This paper identifies a Hessian-based distance measure through PAC-Bayesian analysis, which is shown to correlate well with observed generalization gaps of fine-tuned models. Theoretically, we prove Hessian distance-based generalization bounds for fine-tuned models. We also describe an extended study of fine-tuning against label noise, where overfitting remains a critical problem. We present an algorithm and a generalization error guarantee for this algorithm under a class conditional independent noise model. Empirically, we observe that the Hessian-based distance measure can match the scale of the observed generalization gap of fine-tuned models in practice. We also test our algorithm on several image classification tasks with noisy training labels, showing gains over prior methods and decreases in the Hessian distance measure of the fine-tuned model.","url_abs":"https://arxiv.org/abs/2206.02659v6","url_pdf":"https://arxiv.org/pdf/2206.02659v6.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":"robust-fine-tuning-of-deep-neural-networks","repo_url":"https://github.com/nerdsresearch/robust-fine-tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-fine-tuning-of-deep-neural-networks","repo_url":"https://github.com/neu-statsml-research/robust-fine-tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-fine-tuning-of-deep-neural-networks","repo_url":"https://github.com/virtuosoresearch/robust-fine-tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"generalization-bounds","task_name":"Generalization Bounds"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.02659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02659"}},"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/VirtuosoResearch/Robust-fine-tuning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nerdsresearch/robust-fine-tuning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/virtuosoresearch/robust-fine-tuning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neu-statsml-research/robust-fine-tuning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":3,"ran":2,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":11,"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":"7d8eaf5537f699e4","entry":"np2th","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/model/modeling_resnet.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/modeling_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d8eaf5537f699e4"}},{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/model/modeling_vit.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/modeling_vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"5dcb4148be3fcbaf","entry":"accuracy","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/model/metric.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/metric.py","link_basis":"harvester_set","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":"5dcb4148be3fcbaf"}},{"code_sha256_prefix":"b0f916df39e78ae5","entry":"conv1x1","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/model/modeling_resnet.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/modeling_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0f916df39e78ae5"}},{"code_sha256_prefix":"4e5bf13dbdc4f008","entry":"conv3x3","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/model/modeling_resnet.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/modeling_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e5bf13dbdc4f008"}},{"code_sha256_prefix":"f508a1f840aee873","entry":"custom_kl_div","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/model/loss.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/loss.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f508a1f840aee873"}},{"code_sha256_prefix":"61cc9667c37ecd27","entry":"top_k_acc","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/model/metric.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/metric.py","link_basis":"harvester_set","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":"61cc9667c37ecd27"}},{"code_sha256_prefix":"0a6dcb72cc637951","entry":"get_classes","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/data_loader/mini_domain_net.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/data_loader/mini_domain_net.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":"0a6dcb72cc637951"}},{"code_sha256_prefix":"fa25db77d8a7f54f","entry":"get_loaders","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/data_loader/mini_domain_net.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/data_loader/mini_domain_net.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":"fa25db77d8a7f54f"}},{"code_sha256_prefix":"8c2db3d4435816c0","entry":"nll_loss","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/model/loss.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/loss.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":"8c2db3d4435816c0"}},{"code_sha256_prefix":"aab5cc3f4ce427b5","entry":"perturbe_model_weights","repo":"VirtuosoResearch/Robust-fine-tuning","repo_kind":"official","path":"exps_on_image_datasets/compute_noise_stability.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/compute_noise_stability.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":"aab5cc3f4ce427b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}