{"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/topological-recurrent-neural-network-for","title":"Topological Recurrent Neural Network for Diffusion Prediction","arxiv_id":"1711.10162","date":"2017-11-28","proceeding":null,"authors":["Jia Wang","Vincent W. Zheng","Zemin Liu","Kevin Chen-Chuan Chang"],"abstract":"In this paper, we study the problem of using representation learning to\nassist information diffusion prediction on graphs. In particular, we aim at\nestimating the probability of an inactive node to be activated next in a\ncascade. Despite the success of recent deep learning methods for diffusion, we\nfind that they often underexplore the cascade structure. We consider a cascade\nas not merely a sequence of nodes ordered by their activation time stamps;\ninstead, it has a richer structure indicating the diffusion process over the\ndata graph. As a result, we introduce a new data model, namely diffusion\ntopologies, to fully describe the cascade structure. We find it challenging to\nmodel diffusion topologies, which are dynamic directed acyclic graphs (DAGs),\nwith the existing neural networks. Therefore, we propose a novel topological\nrecurrent neural network, namely Topo-LSTM, for modeling dynamic DAGs. We\ncustomize Topo-LSTM for the diffusion prediction task, and show it improves the\nstate-of-the-art baselines, by 20.1%--56.6% (MAP) relatively, across multiple\nreal-world data sets. Our code and data sets are available online at\nhttps://github.com/vwz/topolstm.","url_abs":"http://arxiv.org/abs/1711.10162v2","url_pdf":"http://arxiv.org/pdf/1711.10162v2.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":"topological-recurrent-neural-network-for","repo_url":"https://github.com/vwz/topolstm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}