{"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/smooth-variational-graph-embeddings-for","title":"Smooth Variational Graph Embeddings for Efficient Neural Architecture Search","arxiv_id":"2010.04683","date":"2020-10-09","proceeding":null,"authors":["Jovita Lukasik","David Friede","Arber Zela","Frank Hutter","Margret Keuper"],"abstract":"Neural architecture search (NAS) has recently been addressed from various directions, including discrete, sampling-based methods and efficient differentiable approaches. While the former are notoriously expensive, the latter suffer from imposing strong constraints on the search space. Architecture optimization from a learned embedding space for example through graph neural network based variational autoencoders builds a middle ground and leverages advantages from both sides. Such approaches have recently shown good performance on several benchmarks. Yet, their stability and predictive power heavily depends on their capacity to reconstruct networks from the embedding space. In this paper, we propose a two-sided variational graph autoencoder, which allows to smoothly encode and accurately reconstruct neural architectures from various search spaces. We evaluate the proposed approach on neural architectures defined by the ENAS approach, the NAS-Bench-101 and the NAS-Bench-201 search space and show that our smooth embedding space allows to directly extrapolate the performance prediction to architectures outside the seen domain (e.g. with more operations). Thus, it facilitates to predict good network architectures even without expensive Bayesian optimization or reinforcement learning.","url_abs":"https://arxiv.org/abs/2010.04683v3","url_pdf":"https://arxiv.org/pdf/2010.04683v3.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":"smooth-variational-graph-embeddings-for","repo_url":"https://github.com/automl/SVGe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"smooth-variational-graph-embeddings-for","repo_url":"https://github.com/jovitalukasik/SVGe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.04683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04683"}},"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/automl/SVGe","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jovitalukasik/SVGe","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"repositories":2}},"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":"b6fa639365ad18db","entry":"generate_adj","repo":"automl/SVGe","repo_kind":"official","path":"Extrapolation_Ability/eval_extrapolation.py","file_url":"https://github.com/automl/SVGe/blob/HEAD/Extrapolation_Ability/eval_extrapolation.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":"b6fa639365ad18db"}},{"code_sha256_prefix":"7e6eb552e178473b","entry":"parse_graph_to_nx","repo":"automl/SVGe","repo_kind":"official","path":"Extrapolation_Ability/eval_extrapolation.py","file_url":"https://github.com/automl/SVGe/blob/HEAD/Extrapolation_Ability/eval_extrapolation.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":"7e6eb552e178473b"}},{"code_sha256_prefix":"fbdbd8d75bfe83f2","entry":"batch2graph","repo":"jovitalukasik/SVGe","repo_kind":"official","path":"models/SVGe.py","file_url":"https://github.com/jovitalukasik/SVGe/blob/HEAD/models/SVGe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fbdbd8d75bfe83f2"}},{"code_sha256_prefix":"6c74edc2c0dc695e","entry":"compute_kernel_numpy","repo":"jovitalukasik/SVGe","repo_kind":"official","path":"Bayesian_Optimization/gauss.py","file_url":"https://github.com/jovitalukasik/SVGe/blob/HEAD/Bayesian_Optimization/gauss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c74edc2c0dc695e"}},{"code_sha256_prefix":"4d5aa0fb9e228553","entry":"edges2index","repo":"jovitalukasik/SVGe","repo_kind":"official","path":"models/SVGe.py","file_url":"https://github.com/jovitalukasik/SVGe/blob/HEAD/models/SVGe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d5aa0fb9e228553"}},{"code_sha256_prefix":"b877cbe6c942ca45","entry":"get_highest_over_time","repo":"jovitalukasik/SVGe","repo_kind":"official","path":"Bayesian_Optimization/summarize.py","file_url":"https://github.com/jovitalukasik/SVGe/blob/HEAD/Bayesian_Optimization/summarize.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b877cbe6c942ca45"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}