{"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/relational-recurrent-neural-networks","title":"Relational recurrent neural networks","arxiv_id":"1806.01822","date":"2018-06-05","proceeding":"NeurIPS 2018 12","authors":["Adam Santoro","Ryan Faulkner","David Raposo","Jack Rae","Mike Chrzanowski","Theophane Weber","Daan Wierstra","Oriol Vinyals","Razvan Pascanu","Timothy Lillicrap"],"abstract":"Memory-based neural networks model temporal data by leveraging an ability to\nremember information for long periods. It is unclear, however, whether they\nalso have an ability to perform complex relational reasoning with the\ninformation they remember. Here, we first confirm our intuitions that standard\nmemory architectures may struggle at tasks that heavily involve an\nunderstanding of the ways in which entities are connected -- i.e., tasks\ninvolving relational reasoning. We then improve upon these deficits by using a\nnew memory module -- a \\textit{Relational Memory Core} (RMC) -- which employs\nmulti-head dot product attention to allow memories to interact. Finally, we\ntest the RMC on a suite of tasks that may profit from more capable relational\nreasoning across sequential information, and show large gains in RL domains\n(e.g. Mini PacMan), program evaluation, and language modeling, achieving\nstate-of-the-art results on the WikiText-103, Project Gutenberg, and GigaWord\ndatasets.","url_abs":"http://arxiv.org/abs/1806.01822v2","url_pdf":"http://arxiv.org/pdf/1806.01822v2.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":"relational-recurrent-neural-networks","repo_url":"https://github.com/L0SG/relational-rnn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"relational-recurrent-neural-networks","repo_url":"https://github.com/cheonbok94/Pytorch-Relational-Recurrent-Neural-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"LSTM (RMC)","rank_in_archive_order":72,"of":89,"metrics":{"Test perplexity":"31.6","Validation perplexity":"30.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.01822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01822"}},"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/L0SG/relational-rnn-pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cheonbok94/Pytorch-Relational-Recurrent-Neural-networks","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":5},"by_repo_kind":{"listed":{"samples":6,"ran":1,"repositories":2}},"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":"a81c5fb0b9535995","entry":"repackage_hidden","repo":"L0SG/relational-rnn-pytorch","repo_kind":"listed","path":"train_rnn.py","file_url":"https://github.com/L0SG/relational-rnn-pytorch/blob/HEAD/train_rnn.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a81c5fb0b9535995"}},{"code_sha256_prefix":"da30d1718326dbeb","entry":"accuracy_score","repo":"L0SG/relational-rnn-pytorch","repo_kind":"listed","path":"train_embeddings.py","file_url":"https://github.com/L0SG/relational-rnn-pytorch/blob/HEAD/train_embeddings.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da30d1718326dbeb"}},{"code_sha256_prefix":"b52ce48393b9604b","entry":"get_batch","repo":"L0SG/relational-rnn-pytorch","repo_kind":"listed","path":"train_embeddings.py","file_url":"https://github.com/L0SG/relational-rnn-pytorch/blob/HEAD/train_embeddings.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b52ce48393b9604b"}},{"code_sha256_prefix":"89a8d007cc892d74","entry":"get_example","repo":"L0SG/relational-rnn-pytorch","repo_kind":"listed","path":"train_nth_farthest.py","file_url":"https://github.com/L0SG/relational-rnn-pytorch/blob/HEAD/train_nth_farthest.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"89a8d007cc892d74"}},{"code_sha256_prefix":"508cfb82d084f33d","entry":"load_vocab","repo":"cheonbok94/Pytorch-Relational-Recurrent-Neural-networks","repo_kind":"listed","path":"utils/data.py","file_url":"https://github.com/cheonbok94/Pytorch-Relational-Recurrent-Neural-networks/blob/HEAD/utils/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"508cfb82d084f33d"}},{"code_sha256_prefix":"79e0326d49cf928c","entry":"one_hot_encode","repo":"L0SG/relational-rnn-pytorch","repo_kind":"listed","path":"train_nth_farthest.py","file_url":"https://github.com/L0SG/relational-rnn-pytorch/blob/HEAD/train_nth_farthest.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79e0326d49cf928c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}