{"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/skip-rnn-learning-to-skip-state-updates-in","title":"Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks","arxiv_id":"1708.06834","date":"2017-08-22","proceeding":"ICLR 2018 1","authors":["Victor Campos","Brendan Jou","Xavier Giro-i-Nieto","Jordi Torres","Shih-Fu Chang"],"abstract":"Recurrent Neural Networks (RNNs) continue to show outstanding performance in\nsequence modeling tasks. However, training RNNs on long sequences often face\nchallenges like slow inference, vanishing gradients and difficulty in capturing\nlong term dependencies. In backpropagation through time settings, these issues\nare tightly coupled with the large, sequential computational graph resulting\nfrom unfolding the RNN in time. We introduce the Skip RNN model which extends\nexisting RNN models by learning to skip state updates and shortens the\neffective size of the computational graph. This model can also be encouraged to\nperform fewer state updates through a budget constraint. We evaluate the\nproposed model on various tasks and show how it can reduce the number of\nrequired RNN updates while preserving, and sometimes even improving, the\nperformance of the baseline RNN models. Source code is publicly available at\nhttps://imatge-upc.github.io/skiprnn-2017-telecombcn/ .","url_abs":"http://arxiv.org/abs/1708.06834v3","url_pdf":"http://arxiv.org/pdf/1708.06834v3.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":"skip-rnn-learning-to-skip-state-updates-in","repo_url":"https://github.com/imatge-upc/skiprnn-2017-telecombcn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"skip-rnn-learning-to-skip-state-updates-in","repo_url":"https://github.com/gitabcworld/skiprnn_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"skip-rnn-learning-to-skip-state-updates-in","repo_url":"https://github.com/ht1221/leap-lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.06834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.06834"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/ht1221/leap-lstm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gitabcworld/skiprnn_pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/imatge-upc/skiprnn-2017-telecombcn","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":3,"ran_violates":1,"ran_honours":1},"by_repo_kind":{"listed":{"samples":5,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"c66f1653246a3f00","entry":"generate_batch","repo":"gitabcworld/skiprnn_pytorch","repo_kind":"listed","path":"01_adding_task.py","file_url":"https://github.com/gitabcworld/skiprnn_pytorch/blob/HEAD/01_adding_task.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c66f1653246a3f00"}},{"code_sha256_prefix":"a74297a41b6da2e5","entry":"generate_batch","repo":"gitabcworld/skiprnn_pytorch","repo_kind":"listed","path":"02_frequency_discrimination_task.py","file_url":"https://github.com/gitabcworld/skiprnn_pytorch/blob/HEAD/02_frequency_discrimination_task.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a74297a41b6da2e5"}},{"code_sha256_prefix":"d227ddcb957cbd98","entry":"generate_example","repo":"gitabcworld/skiprnn_pytorch","repo_kind":"listed","path":"01_adding_task.py","file_url":"https://github.com/gitabcworld/skiprnn_pytorch/blob/HEAD/01_adding_task.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d227ddcb957cbd98"}},{"code_sha256_prefix":"deb7da5aef1d1b5f","entry":"generate_example","repo":"gitabcworld/skiprnn_pytorch","repo_kind":"listed","path":"02_frequency_discrimination_task.py","file_url":"https://github.com/gitabcworld/skiprnn_pytorch/blob/HEAD/02_frequency_discrimination_task.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"deb7da5aef1d1b5f"}},{"code_sha256_prefix":"dd51789ac2ee4cf6","entry":"random_disjoint_interval","repo":"gitabcworld/skiprnn_pytorch","repo_kind":"listed","path":"02_frequency_discrimination_task.py","file_url":"https://github.com/gitabcworld/skiprnn_pytorch/blob/HEAD/02_frequency_discrimination_task.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd51789ac2ee4cf6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}