{"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/encoding-robust-representation-for-graph","title":"Encoding Robust Representation for Graph Generation","arxiv_id":"1809.10851","date":"2018-09-28","proceeding":null,"authors":["Dongmian Zou","Gilad Lerman"],"abstract":"Generative networks have made it possible to generate meaningful signals such\nas images and texts from simple noise. Recently, generative methods based on\nGAN and VAE were developed for graphs and graph signals. However, the\nmathematical properties of these methods are unclear, and training good\ngenerative models is difficult. This work proposes a graph generation model\nthat uses a recent adaptation of Mallat's scattering transform to graphs. The\nproposed model is naturally composed of an encoder and a decoder. The encoder\nis a Gaussianized graph scattering transform, which is robust to signal and\ngraph manipulation. The decoder is a simple fully connected network that is\nadapted to specific tasks, such as link prediction, signal generation on graphs\nand full graph and signal generation. The training of our proposed system is\nefficient since it is only applied to the decoder and the hardware requirements\nare moderate. Numerical results demonstrate state-of-the-art performance of the\nproposed system for both link prediction and graph and signal generation.","url_abs":"http://arxiv.org/abs/1809.10851v2","url_pdf":"http://arxiv.org/pdf/1809.10851v2.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":"encoding-robust-representation-for-graph","repo_url":"https://github.com/dmzou/SCAT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-citeseer-biased-evaluation","task":"Link Prediction","dataset":"Citeseer (biased evaluation)","model":"SCAT (half of negative examples with 0 features)","rank_in_archive_order":2,"of":2,"metrics":{"AP":"97.57","AUC":"97.27"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-cora-biased-evaluation","task":"Link Prediction","dataset":"Cora (biased evaluation)","model":"SCAT (half of negative examples with 0 features)","rank_in_archive_order":2,"of":2,"metrics":{"AP":"94.63","AUC":"94.48"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-pubmed-biased-evaluation","task":"Link Prediction","dataset":"Pubmed (biased evaluation)","model":"SCAT (half of negative examples with 0 features)","rank_in_archive_order":2,"of":2,"metrics":{"AP":"97.19","AUC":"97.52"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}