{"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/trellis-networks-for-sequence-modeling","title":"Trellis Networks for Sequence Modeling","arxiv_id":"1810.06682","date":"2018-10-15","proceeding":"ICLR 2019 5","authors":["Shaojie Bai","J. Zico Kolter","Vladlen Koltun"],"abstract":"We present trellis networks, a new architecture for sequence modeling. On the\none hand, a trellis network is a temporal convolutional network with special\nstructure, characterized by weight tying across depth and direct injection of\nthe input into deep layers. On the other hand, we show that truncated recurrent\nnetworks are equivalent to trellis networks with special sparsity structure in\ntheir weight matrices. Thus trellis networks with general weight matrices\ngeneralize truncated recurrent networks. We leverage these connections to\ndesign high-performing trellis networks that absorb structural and algorithmic\nelements from both recurrent and convolutional models. Experiments demonstrate\nthat trellis networks outperform the current state of the art methods on a\nvariety of challenging benchmarks, including word-level language modeling and\ncharacter-level language modeling tasks, and stress tests designed to evaluate\nlong-term memory retention. The code is available at\nhttps://github.com/locuslab/trellisnet .","url_abs":"http://arxiv.org/abs/1810.06682v2","url_pdf":"http://arxiv.org/pdf/1810.06682v2.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":"trellis-networks-for-sequence-modeling","repo_url":"https://github.com/locuslab/trellisnet","is_official":1,"mentioned_in_paper":1,"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":"sequential-image-classification","task_name":"Sequential Image Classification"}],"methods":[{"method_slug":"weight-tying","method_name":"Weight Tying"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-penn-treebank-character","task":"Language Modelling","dataset":"Penn Treebank (Character Level)","model":"Trellis Network","rank_in_archive_order":4,"of":20,"metrics":{"Bit per Character (BPC)":"1.158","Number of params":"13.4M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-penn-treebank-word","task":"Language Modelling","dataset":"Penn Treebank (Word Level)","model":"Trellis Network","rank_in_archive_order":19,"of":43,"metrics":{"Test perplexity":"54.19"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"Trellis Network","rank_in_archive_order":67,"of":89,"metrics":{"Test perplexity":"29.19"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-image-classification-on-sequential-1","task":"Sequential Image Classification","dataset":"Sequential CIFAR-10","model":"Trellis Network","rank_in_archive_order":8,"of":13,"metrics":{"Unpermuted Accuracy":"73.42%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.06682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06682"}},"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/locuslab/trellisnet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"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":"f6b944f50d3f15ae","entry":"count_parameters","repo":"locuslab/trellisnet","repo_kind":"official","path":"TrellisNet/seq_MNIST_CIFAR/utils.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/seq_MNIST_CIFAR/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"4372bb4533fd1936","entry":"repackage_hidden","repo":"locuslab/trellisnet","repo_kind":"official","path":"TrellisNet/word_PTB/utils.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/word_PTB/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"code_sha256_prefix":"82c927821e8de854","entry":"batchify","repo":"locuslab/trellisnet","repo_kind":"official","path":"TrellisNet/word_PTB/utils.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/word_PTB/utils.py","link_basis":"first_harvest_node","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":"82c927821e8de854"}},{"code_sha256_prefix":"1e3a5f83246ebc4f","entry":"char_tensor","repo":"locuslab/trellisnet","repo_kind":"official","path":"TrellisNet/char_PTB/utils.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/char_PTB/utils.py","link_basis":"first_harvest_node","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":"1e3a5f83246ebc4f"}},{"code_sha256_prefix":"512e27f728a83a6b","entry":"data_generator","repo":"locuslab/trellisnet","repo_kind":"official","path":"TrellisNet/seq_MNIST_CIFAR/utils.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/seq_MNIST_CIFAR/utils.py","link_basis":"first_harvest_node","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":"512e27f728a83a6b"}},{"code_sha256_prefix":"ad3308380ac371b2","entry":"embedded_dropout","repo":"locuslab/trellisnet","repo_kind":"official","path":"TrellisNet/optimizations.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/optimizations.py","link_basis":"first_harvest_node","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":"ad3308380ac371b2"}},{"code_sha256_prefix":"ae7fc1f2f81e0504","entry":"repackage_hidden4","repo":"locuslab/trellisnet","repo_kind":"official","path":"TrellisNet/char_PTB/utils.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/char_PTB/utils.py","link_basis":"first_harvest_node","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":"ae7fc1f2f81e0504"}},{"code_sha256_prefix":"4bf00e788db9f349","entry":"weight_norm","repo":"locuslab/trellisnet","repo_kind":"official","path":"TrellisNet/optimizations.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/optimizations.py","link_basis":"plan_row","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":"4bf00e788db9f349"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}