{"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/towards-unifying-neural-architecture-space","title":"How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?","arxiv_id":"1910.00780","date":"2019-10-02","proceeding":"CVPR 2021 1","authors":["Kartikeya Bhardwaj","Guihong Li","Radu Marculescu"],"abstract":"DenseNets introduce concatenation-type skip connections that achieve state-of-the-art accuracy in several computer vision tasks. In this paper, we reveal that the topology of the concatenation-type skip connections is closely related to the gradient propagation which, in turn, enables a predictable behavior of DNNs' test performance. To this end, we introduce a new metric called NN-Mass to quantify how effectively information flows through DNNs. Moreover, we empirically show that NN-Mass also works for other types of skip connections, e.g., for ResNets, Wide-ResNets (WRNs), and MobileNets, which contain addition-type skip connections (i.e., residuals or inverted residuals). As such, for both DenseNet-like CNNs and ResNets/WRNs/MobileNets, our theoretically grounded NN-Mass can identify models with similar accuracy, despite having significantly different size/compute requirements. Detailed experiments on both synthetic and real datasets (e.g., MNIST, CIFAR-10, CIFAR-100, ImageNet) provide extensive evidence for our insights. Finally, the closed-form equation of our NN-Mass enables us to design significantly compressed DenseNets (for CIFAR-10) and MobileNets (for ImageNet) directly at initialization without time-consuming training and/or searching.","url_abs":"https://arxiv.org/abs/1910.00780v3","url_pdf":"https://arxiv.org/pdf/1910.00780v3.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":"towards-unifying-neural-architecture-space","repo_url":"https://github.com/SLDGroup/NN_Mass","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-unifying-neural-architecture-space","repo_url":"https://github.com/arm-software/ml-restructurable-activation-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.00780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00780"}},"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/SLDGroup/NN_Mass","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arm-software/ml-restructurable-activation-networks","reach":{"status":"unanswered"}}],"summary":{"ran_violates":1,"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"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":"1d9cfaf4282b4c13","entry":"accuracy","repo":"SLDGroup/NN_Mass","repo_kind":"listed","path":"train_mlp.py","file_url":"https://github.com/SLDGroup/NN_Mass/blob/HEAD/train_mlp.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d9cfaf4282b4c13"}},{"code_sha256_prefix":"4800dd5ec9240018","entry":"test","repo":"SLDGroup/NN_Mass","repo_kind":"listed","path":"train_cifar.py","file_url":"https://github.com/SLDGroup/NN_Mass/blob/HEAD/train_cifar.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4800dd5ec9240018"}},{"code_sha256_prefix":"c0bd5cd7c711d4d1","entry":"train","repo":"SLDGroup/NN_Mass","repo_kind":"listed","path":"train_mlp.py","file_url":"https://github.com/SLDGroup/NN_Mass/blob/HEAD/train_mlp.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c0bd5cd7c711d4d1"}},{"code_sha256_prefix":"35d00fe15613b708","entry":"train","repo":"SLDGroup/NN_Mass","repo_kind":"listed","path":"train_cifar.py","file_url":"https://github.com/SLDGroup/NN_Mass/blob/HEAD/train_cifar.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35d00fe15613b708"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}