{"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/hypermoe-towards-better-mixture-of-experts","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","arxiv_id":"2402.12656","date":"2024-02-20","proceeding":null,"authors":["Hao Zhao","Zihan Qiu","Huijia Wu","Zili Wang","Zhaofeng He","Jie Fu"],"abstract":"The Mixture of Experts (MoE) for language models has been proven effective in augmenting the capacity of models by dynamically routing each input token to a specific subset of experts for processing. Despite the success, most existing methods face a challenge for balance between sparsity and the availability of expert knowledge: enhancing performance through increased use of expert knowledge often results in diminishing sparsity during expert selection. To mitigate this contradiction, we propose HyperMoE, a novel MoE framework built upon Hypernetworks. This framework integrates the computational processes of MoE with the concept of knowledge transferring in multi-task learning. Specific modules generated based on the information of unselected experts serve as supplementary information, which allows the knowledge of experts not selected to be used while maintaining selection sparsity. Our comprehensive empirical evaluations across multiple datasets and backbones establish that HyperMoE significantly outperforms existing MoE methods under identical conditions concerning the number of experts.","url_abs":"https://arxiv.org/abs/2402.12656v4","url_pdf":"https://arxiv.org/pdf/2402.12656v4.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":"hypermoe-towards-better-mixture-of-experts","repo_url":"https://github.com/bumble666/hypermoe_early_version","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.12656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12656"}},"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/bumble666/hypermoe_early_version","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Bumble666/Hyper_MoE","reach":null}],"summary":{"ran":11,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":14,"ran":9,"repositories":1},"found_in_text":{"samples":4,"ran":3,"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":"7fa2bef8aa39823f","entry":"AdapterLayer","repo":"Bumble666/Hyper_MoE","repo_kind":"found_in_text","path":"gpt-2-moe/transformers/models/layers.py","file_url":"https://github.com/Bumble666/Hyper_MoE/blob/HEAD/gpt-2-moe/transformers/models/layers.py","link_basis":"first_harvest_node","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":"7fa2bef8aa39823f"}},{"code_sha256_prefix":"3e2fbf364e529352","entry":"SparseDispatcher","repo":"Bumble666/Hyper_MoE","repo_kind":"found_in_text","path":"gpt-2-moe/transformers/models/layers.py","file_url":"https://github.com/Bumble666/Hyper_MoE/blob/HEAD/gpt-2-moe/transformers/models/layers.py","link_basis":"first_harvest_node","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":"3e2fbf364e529352"}},{"code_sha256_prefix":"743ceb9025a7955d","entry":"booleans_processing","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modeling_tf_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_tf_utils.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":"743ceb9025a7955d"}},{"code_sha256_prefix":"5168a172bbb363a5","entry":"convert_pytorch_state_dict_to_flax","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modeling_flax_pytorch_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_flax_pytorch_utils.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":"5168a172bbb363a5"}},{"code_sha256_prefix":"3c1eb64dde6b86af","entry":"dummy_loss","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modeling_tf_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_tf_utils.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":"3c1eb64dde6b86af"}},{"code_sha256_prefix":"ccaa0edba373622c","entry":"get_imports","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/dynamic_module_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/dynamic_module_utils.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":"ccaa0edba373622c"}},{"code_sha256_prefix":"dd8f7751ef859581","entry":"infer_metric_tags_from_eval_results","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modelcard.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modelcard.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":"dd8f7751ef859581"}},{"code_sha256_prefix":"6a3959a0ffd36577","entry":"keras_serializable","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modeling_tf_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_tf_utils.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":"6a3959a0ffd36577"}},{"code_sha256_prefix":"7e4c76ff93dbad95","entry":"noisy_top_k_gating_mixing","repo":"Bumble666/Hyper_MoE","repo_kind":"found_in_text","path":"gpt-2-moe/transformers/models/layers.py","file_url":"https://github.com/Bumble666/Hyper_MoE/blob/HEAD/gpt-2-moe/transformers/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e4c76ff93dbad95"}},{"code_sha256_prefix":"a4491b45d19b7a39","entry":"parse_keras_history","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modelcard.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modelcard.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":"a4491b45d19b7a39"}},{"code_sha256_prefix":"a66d2b78670c85e1","entry":"quick_gelu","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modeling_flax_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_flax_utils.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":"a66d2b78670c85e1"}},{"code_sha256_prefix":"61779b0406a59cfc","entry":"rename_key_and_reshape_tensor","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modeling_flax_pytorch_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_flax_pytorch_utils.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":"61779b0406a59cfc"}},{"code_sha256_prefix":"89f7e4ccbdd62673","entry":"MoE","repo":"Bumble666/Hyper_MoE","repo_kind":"found_in_text","path":"gpt-2-moe/transformers/models/layers.py","file_url":"https://github.com/Bumble666/Hyper_MoE/blob/HEAD/gpt-2-moe/transformers/models/layers.py","link_basis":"first_harvest_node","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":"89f7e4ccbdd62673"}},{"code_sha256_prefix":"9d98806acb3144b7","entry":"dtype_byte_size","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modeling_flax_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_flax_utils.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":"9d98806acb3144b7"}},{"code_sha256_prefix":"e3ce70ca9258800e","entry":"flax_shard_checkpoint","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modeling_flax_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_flax_utils.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":"e3ce70ca9258800e"}},{"code_sha256_prefix":"00cc853a73f3aeb6","entry":"get_relative_import_files","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/dynamic_module_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/dynamic_module_utils.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":"00cc853a73f3aeb6"}},{"code_sha256_prefix":"450aeffe7f80f917","entry":"get_relative_imports","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/dynamic_module_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/dynamic_module_utils.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":"450aeffe7f80f917"}},{"code_sha256_prefix":"ec7b1528a936234d","entry":"is_hf_dataset","repo":"bumble666/hypermoe_early_version","repo_kind":"official","path":"gpt-2-moe/transformers/modelcard.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modelcard.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":"ec7b1528a936234d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}