{"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/deepcas-an-end-to-end-predictor-of","title":"DeepCas: an End-to-end Predictor of Information Cascades","arxiv_id":"1611.05373","date":"2016-11-16","proceeding":null,"authors":["Cheng Li","Jiaqi Ma","Xiaoxiao Guo","Qiaozhu Mei"],"abstract":"Information cascades, effectively facilitated by most social network\nplatforms, are recognized as a major factor in almost every social success and\ndisaster in these networks. Can cascades be predicted? While many believe that\nthey are inherently unpredictable, recent work has shown that some key\nproperties of information cascades, such as size, growth, and shape, can be\npredicted by a machine learning algorithm that combines many features. These\npredictors all depend on a bag of hand-crafting features to represent the\ncascade network and the global network structure. Such features, always\ncarefully and sometimes mysteriously designed, are not easy to extend or to\ngeneralize to a different platform or domain.\n  Inspired by the recent successes of deep learning in multiple data mining\ntasks, we investigate whether an end-to-end deep learning approach could\neffectively predict the future size of cascades. Such a method automatically\nlearns the representation of individual cascade graphs in the context of the\nglobal network structure, without hand-crafted features and heuristics. We find\nthat node embeddings fall short of predictive power, and it is critical to\nlearn the representation of a cascade graph as a whole. We present algorithms\nthat learn the representation of cascade graphs in an end-to-end manner, which\nsignificantly improve the performance of cascade prediction over strong\nbaselines that include feature based methods, node embedding methods, and graph\nkernel methods. Our results also provide interesting implications for cascade\nprediction in general.","url_abs":"http://arxiv.org/abs/1611.05373v1","url_pdf":"http://arxiv.org/pdf/1611.05373v1.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":"deepcas-an-end-to-end-predictor-of","repo_url":"https://github.com/chengli-um/DeepCas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1611.05373","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}