{"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/variational-graph-recurrent-neural-networks","title":"Variational Graph Recurrent Neural Networks","arxiv_id":"1908.09710","date":"2019-08-26","proceeding":"NeurIPS 2019 12","authors":["Ehsan Hajiramezanali","Arman Hasanzadeh","Nick Duffield","Krishna R. Narayanan","Mingyuan Zhou","Xiaoning Qian"],"abstract":"Representation learning over graph structured data has been mostly studied in static graph settings while efforts for modeling dynamic graphs are still scant. In this paper, we develop a novel hierarchical variational model that introduces additional latent random variables to jointly model the hidden states of a graph recurrent neural network (GRNN) to capture both topology and node attribute changes in dynamic graphs. We argue that the use of high-level latent random variables in this variational GRNN (VGRNN) can better capture potential variability observed in dynamic graphs as well as the uncertainty of node latent representation. With semi-implicit variational inference developed for this new VGRNN architecture (SI-VGRNN), we show that flexible non-Gaussian latent representations can further help dynamic graph analytic tasks. Our experiments with multiple real-world dynamic graph datasets demonstrate that SI-VGRNN and VGRNN consistently outperform the existing baseline and state-of-the-art methods by a significant margin in dynamic link prediction.","url_abs":"https://arxiv.org/abs/1908.09710v3","url_pdf":"https://arxiv.org/pdf/1908.09710v3.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":"variational-graph-recurrent-neural-networks","repo_url":"https://github.com/VGraphRNN/VGRNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"variational-graph-recurrent-neural-networks","repo_url":"https://github.com/marlin-codes/HTGN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"dynamic-link-prediction","task_name":"Dynamic Link Prediction"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dynamic-link-prediction-on-dblp-temporal","task":"Dynamic Link Prediction","dataset":"DBLP Temporal","model":"VGRNN","rank_in_archive_order":3,"of":7,"metrics":{"AP":"87.77","AUC":"85.95"},"uses_additional_data":false},{"leaderboard":"/sota/dynamic-link-prediction-on-dblp-temporal","task":"Dynamic Link Prediction","dataset":"DBLP Temporal","model":"SI-VGRNN","rank_in_archive_order":4,"of":7,"metrics":{"AP":"88.36","AUC":"85.45"},"uses_additional_data":false},{"leaderboard":"/sota/dynamic-link-prediction-on-enron-email","task":"Dynamic Link Prediction","dataset":"Enron Emails","model":"SI-VGRNN","rank_in_archive_order":2,"of":7,"metrics":{"AP":"93.93","AUC":"94.44"},"uses_additional_data":false},{"leaderboard":"/sota/dynamic-link-prediction-on-enron-email","task":"Dynamic Link Prediction","dataset":"Enron Emails","model":"VGRNN","rank_in_archive_order":4,"of":7,"metrics":{"AP":"93.10","AUC":"93.29"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.09710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09710"}},"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/marlin-codes/HTGN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VGraphRNN/VGRNN","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"cb2d801625fc35f2","entry":"tuple_to_array","repo":"VGraphRNN/VGRNN","repo_kind":"official","path":"VGRNN_detection.py","file_url":"https://github.com/VGraphRNN/VGRNN/blob/HEAD/VGRNN_detection.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb2d801625fc35f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}