{"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/tafe-net-task-aware-feature-embeddings-for","title":"Deep Mixture of Experts via Shallow Embedding","arxiv_id":"1806.01531","date":"2018-06-05","proceeding":null,"authors":["Xin Wang","Fisher Yu","Lisa Dunlap","Yi-An Ma","Ruth Wang","Azalia Mirhoseini","Trevor Darrell","Joseph E. Gonzalez"],"abstract":"Larger networks generally have greater representational power at the cost of\nincreased computational complexity. Sparsifying such networks has been an\nactive area of research but has been generally limited to static regularization\nor dynamic approaches using reinforcement learning. We explore a mixture of\nexperts (MoE) approach to deep dynamic routing, which activates certain experts\nin the network on a per-example basis. Our novel DeepMoE architecture increases\nthe representational power of standard convolutional networks by adaptively\nsparsifying and recalibrating channel-wise features in each convolutional\nlayer. We employ a multi-headed sparse gating network to determine the\nselection and scaling of channels for each input, leveraging exponential\ncombinations of experts within a single convolutional network. Our proposed\narchitecture is evaluated on four benchmark datasets and tasks, and we show\nthat Deep-MoEs are able to achieve higher accuracy with lower computation than\nstandard convolutional networks.","url_abs":"http://arxiv.org/abs/1806.01531v3","url_pdf":"http://arxiv.org/pdf/1806.01531v3.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":"tafe-net-task-aware-feature-embeddings-for","repo_url":"https://github.com/RyanKim17920/DeepMoE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.01531","atlas_url":"https://app.syntology.ai/?focus=1806.01531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01531"}},"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/RyanKim17920/DeepMoE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"listed":{"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":"2a80220dabcb742a","entry":"conv1x1","repo":"RyanKim17920/DeepMoE","repo_kind":"listed","path":"deepResNet.py","file_url":"https://github.com/RyanKim17920/DeepMoE/blob/HEAD/deepResNet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a80220dabcb742a"}},{"code_sha256_prefix":"600ff2c45e0de056","entry":"conv3x3","repo":"RyanKim17920/DeepMoE","repo_kind":"listed","path":"deepResNet.py","file_url":"https://github.com/RyanKim17920/DeepMoE/blob/HEAD/deepResNet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"600ff2c45e0de056"}},{"code_sha256_prefix":"48cdb2a6680c033c","entry":"conv1x1","repo":"RyanKim17920/DeepMoE","repo_kind":"listed","path":"ResNet.py","file_url":"https://github.com/RyanKim17920/DeepMoE/blob/HEAD/ResNet.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":"48cdb2a6680c033c"}},{"code_sha256_prefix":"875b54ff64987752","entry":"conv3x3","repo":"RyanKim17920/DeepMoE","repo_kind":"listed","path":"ResNet.py","file_url":"https://github.com/RyanKim17920/DeepMoE/blob/HEAD/ResNet.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":"875b54ff64987752"}},{"code_sha256_prefix":"0dd83849de669c55","entry":"format_summary","repo":"RyanKim17920/DeepMoE","repo_kind":"listed","path":"flops.py","file_url":"https://github.com/RyanKim17920/DeepMoE/blob/HEAD/flops.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":"0dd83849de669c55"}},{"code_sha256_prefix":"a0ff1e5387c04771","entry":"initialize_model","repo":"RyanKim17920/DeepMoE","repo_kind":"listed","path":"traintest.py","file_url":"https://github.com/RyanKim17920/DeepMoE/blob/HEAD/traintest.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":"a0ff1e5387c04771"}},{"code_sha256_prefix":"010ea6bdb0a3dd55","entry":"initialize_optimizer","repo":"RyanKim17920/DeepMoE","repo_kind":"listed","path":"traintest.py","file_url":"https://github.com/RyanKim17920/DeepMoE/blob/HEAD/traintest.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":"010ea6bdb0a3dd55"}},{"code_sha256_prefix":"ab77a722b7b88e9a","entry":"initialize_scheduler","repo":"RyanKim17920/DeepMoE","repo_kind":"listed","path":"traintest.py","file_url":"https://github.com/RyanKim17920/DeepMoE/blob/HEAD/traintest.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":"ab77a722b7b88e9a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}