{"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/routing-networks-and-the-challenges-of","title":"Routing Networks and the Challenges of Modular and Compositional Computation","arxiv_id":"1904.12774","date":"2019-04-29","proceeding":null,"authors":["Clemens Rosenbaum","Ignacio Cases","Matthew Riemer","Tim Klinger"],"abstract":"Compositionality is a key strategy for addressing combinatorial complexity\nand the curse of dimensionality. Recent work has shown that compositional\nsolutions can be learned and offer substantial gains across a variety of\ndomains, including multi-task learning, language modeling, visual question\nanswering, machine comprehension, and others. However, such models present\nunique challenges during training when both the module parameters and their\ncomposition must be learned jointly. In this paper, we identify several of\nthese issues and analyze their underlying causes. Our discussion focuses on\nrouting networks, a general approach to this problem, and examines empirically\nthe interplay of these challenges and a variety of design decisions. In\nparticular, we consider the effect of how the algorithm decides on module\ncomposition, how the algorithm updates the modules, and if the algorithm uses\nregularization.","url_abs":"http://arxiv.org/abs/1904.12774v1","url_pdf":"http://arxiv.org/pdf/1904.12774v1.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":"routing-networks-and-the-challenges-of","repo_url":"https://github.com/cle-ros/RoutingNetworks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.12774","atlas_url":"https://app.syntology.ai/?focus=1904.12774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12774"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/cle-ros/RoutingNetworks","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2},"by_repo_kind":{"listed":{"samples":2,"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":"a415d1da67633beb","entry":"entropy","repo":"cle-ros/RoutingNetworks","repo_kind":"listed","path":"PytorchRouting/DecisionLayers/Others/RELAX.py","file_url":"https://github.com/cle-ros/RoutingNetworks/blob/HEAD/PytorchRouting/DecisionLayers/Others/RELAX.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a415d1da67633beb"}},{"code_sha256_prefix":"f7a44e38add17d09","entry":"make_samples","repo":"cle-ros/RoutingNetworks","repo_kind":"listed","path":"PytorchRouting/DecisionLayers/Others/RELAX.py","file_url":"https://github.com/cle-ros/RoutingNetworks/blob/HEAD/PytorchRouting/DecisionLayers/Others/RELAX.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7a44e38add17d09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}