{"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/gcn-gan-a-non-linear-temporal-link-prediction","title":"GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networks","arxiv_id":"1901.09165","date":"2019-01-26","proceeding":null,"authors":["Kai Lei","Meng Qin","Bo Bai","Gong Zhang","Min Yang"],"abstract":"In this paper, we generally formulate the dynamics prediction problem of\nvarious network systems (e.g., the prediction of mobility, traffic and\ntopology) as the temporal link prediction task. Different from conventional\ntechniques of temporal link prediction that ignore the potential non-linear\ncharacteristics and the informative link weights in the dynamic network, we\nintroduce a novel non-linear model GCN-GAN to tackle the challenging temporal\nlink prediction task of weighted dynamic networks. The proposed model leverages\nthe benefits of the graph convolutional network (GCN), long short-term memory\n(LSTM) as well as the generative adversarial network (GAN). Thus, the dynamics,\ntopology structure and evolutionary patterns of weighted dynamic networks can\nbe fully exploited to improve the temporal link prediction performance.\nConcretely, we first utilize GCN to explore the local topological\ncharacteristics of each single snapshot and then employ LSTM to characterize\nthe evolving features of the dynamic networks. Moreover, GAN is used to enhance\nthe ability of the model to generate the next weighted network snapshot, which\ncan effectively tackle the sparsity and the wide-value-range problem of edge\nweights in real-life dynamic networks. To verify the model's effectiveness, we\nconduct extensive experiments on four datasets of different network systems and\napplication scenarios. The experimental results demonstrate that our model\nachieves impressive results compared to the state-of-the-art competitors.","url_abs":"http://arxiv.org/abs/1901.09165v1","url_pdf":"http://arxiv.org/pdf/1901.09165v1.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":"gcn-gan-a-non-linear-temporal-link-prediction","repo_url":"https://github.com/yanghaoxie/GCN-GAN-for-Weighted-Dynamic-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.09165","atlas_url":"https://app.syntology.ai/?focus=1901.09165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09165"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/yanghaoxie/GCN-GAN-for-Weighted-Dynamic-Networks","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"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":"e81dbe24b2d431fc","entry":"gen_noise","repo":"yanghaoxie/GCN-GAN-for-Weighted-Dynamic-Networks","repo_kind":"listed","path":"GCN-GAN/LSTM_GAN_GCN.py","file_url":"https://github.com/yanghaoxie/GCN-GAN-for-Weighted-Dynamic-Networks/blob/HEAD/GCN-GAN/LSTM_GAN_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e81dbe24b2d431fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}