{"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/rra-recurrent-residual-attention-for-sequence","title":"RRA: Recurrent Residual Attention for Sequence Learning","arxiv_id":"1709.03714","date":"2017-09-12","proceeding":null,"authors":["Cheng Wang"],"abstract":"In this paper, we propose a recurrent neural network (RNN) with residual\nattention (RRA) to learn long-range dependencies from sequential data. We\npropose to add residual connections across timesteps to RNN, which explicitly\nenhances the interaction between current state and hidden states that are\nseveral timesteps apart. This also allows training errors to be directly\nback-propagated through residual connections and effectively alleviates\ngradient vanishing problem. We further reformulate an attention mechanism over\nresidual connections. An attention gate is defined to summarize the individual\ncontribution from multiple previous hidden states in computing the current\nstate. We evaluate RRA on three tasks: the adding problem, pixel-by-pixel MNIST\nclassification and sentiment analysis on the IMDB dataset. Our experiments\ndemonstrate that RRA yields better performance, faster convergence and more\nstable training compared to a standard LSTM network. Furthermore, RRA shows\nhighly competitive performance to the state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1709.03714v1","url_pdf":"http://arxiv.org/pdf/1709.03714v1.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":"rra-recurrent-residual-attention-for-sequence","repo_url":"https://github.com/JRC1995/Abstractive-Summarization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"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/1709.03714","atlas_url":"https://app.syntology.ai/?focus=1709.03714","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}