Papers › HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts

HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts

20 Feb 2024arXiv:2402.12656archive 2025-07-28

Hao Zhao, Zihan Qiu, Huijia Wu, Zili Wang, Zhaofeng He, Jie Fu

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.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (4 with no instrument failure; 7 where Syntology's instrument failed); found in paper text by Syntology: 4 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

bumble666/hypermoe_early_version officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: 14 samples, 11 ran (7 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 14 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
8ran · our draft was wrong
5ran
4unverified

Licence: 7 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show, each row saying why in its tooltip: for 1, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape; for 1, for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

bumble666/hypermoe_early_version official repository 14 samples, 11 ran (7 instrument-failed) · 3 unverified
booleans_processing in 9 papers gpt-2-moe/transformers/modeling_tf_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 743ceb9025a7955d · report fixture: signature config:MinimalConfig/0/?, output_attentions:bool/0/bool, output_hidden_states:NoneType/0/?, return_dict:bool/0/bool, use_cache:NoneType/0/? · returned dict · level recorded 2026-09-24
convert_pytorch_state_dict_to_flax in 21 papers gpt-2-moe/transformers/modeling_flax_pytorch_utils.py ran Apache-2.0 (permissive) · 5168a172bbb363a5 · report fixture: signature pt_state_dict:dict/0/?, flax_model:MinimalFlaxModel/0/? · returned dict · level recorded 2026-09-24
dummy_loss in 11 papers gpt-2-moe/transformers/modeling_tf_utils.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 3c1eb64dde6b86af · report fixture: signature y_true:EagerTensor/3/float, y_pred:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
get_imports in 16 papers gpt-2-moe/transformers/dynamic_module_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · ccaa0edba373622c · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-24
get_relative_import_files in 28 papers gpt-2-moe/transformers/dynamic_module_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 00cc853a73f3aeb6 · report fixture: signature module_file:str/0/str · returned list · level recorded 2026-09-26
get_relative_imports in 28 papers gpt-2-moe/transformers/dynamic_module_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 450aeffe7f80f917 · report fixture: signature module_file:str/0/str · returned list · level recorded 2026-09-26
infer_metric_tags_from_eval_results in 20 papers gpt-2-moe/transformers/modelcard.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · dd8f7751ef859581 · report fixture: signature eval_results:dict/0/? · returned dict · level recorded 2026-09-24
keras_serializable in 11 papers gpt-2-moe/transformers/modeling_tf_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 6a3959a0ffd36577 · report fixture: signature cls:callable/0/? · returned type · level recorded 2026-09-24
parse_keras_history in 19 papers gpt-2-moe/transformers/modelcard.py ran · our draft was wrong Apache-2.0 (permissive) · a4491b45d19b7a39 · report fixture: returned tuple · level recorded 2026-09-24
quick_gelu in 43 papers gpt-2-moe/transformers/modeling_flax_utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · a66d2b78670c85e1 · report fixture: signature x:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
rename_key_and_reshape_tensor in 22 papers gpt-2-moe/transformers/modeling_flax_pytorch_utils.py ran Apache-2.0 (permissive) · 61779b0406a59cfc · report fixture: signature pt_tuple_key:tuple/1/str, pt_tensor:ndarray/4/float, random_flax_state_dict:dict/0/?, model_prefix:str/0/str · returned tuple · level recorded 2026-09-24
dtype_byte_size in 15 papers gpt-2-moe/transformers/modeling_flax_utils.py unverified Apache-2.0 (permissive) · 9d98806acb3144b7 · report
flax_shard_checkpoint in 15 papers gpt-2-moe/transformers/modeling_flax_utils.py unverified Apache-2.0 (permissive) · e3ce70ca9258800e · report
is_hf_dataset in 20 papers gpt-2-moe/transformers/modelcard.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · ec7b1528a936234d · report
Bumble666/Hyper_MoE found in paper text by Syntology 4 samples, 3 ran (1 instrument-failed) · 1 unverified
AdapterLayer in 5 papers gpt-2-moe/transformers/models/layers.py ran fingerprinted Apache-2.0 (permissive) · 7fa2bef8aa39823f · report fixture: returned AdapterLayer · level recorded 2026-09-22
SparseDispatcher in 7 papers gpt-2-moe/transformers/models/layers.py ran Apache-2.0 (permissive) · 3e2fbf364e529352 · report fixture: returned SparseDispatcher · level recorded 2026-09-22
noisy_top_k_gating_mixing gpt-2-moe/transformers/models/layers.py ran · our draft was wrong Apache-2.0 (permissive) · 7e4c76ff93dbad95 · report fixture: signature layer:callable/0/?, x:Tensor/2/float, train:bool/0/bool, noise_epsilon:float/0/float · returned tuple · level recorded 2026-09-22
MoE in 10 papers gpt-2-moe/transformers/models/layers.py unverified Apache-2.0 (permissive) · 89f7e4ccbdd62673 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for HyperMoE (graph method: HyperMoE). 7 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. MoE entry · level 0 · unverified · 89f7e4ccbdd62673
  2. AdapterLayer helper · level 1 · ran · 7fa2bef8aa39823f
  3. SparseDispatcher helper · level 1 · ran · 3e2fbf364e529352
  4. cv_squared metric · level 1 · ran · our draft was wrong · abbff004073dc773
  5. noisy_top_k_gating_mixing model · level 1 · ran · our draft was wrong · 7e4c76ff93dbad95
  6. _gates_to_load helper · level 1 · ran · honoured contract · bd49c412803e1b6e
  7. _prob_in_top_k helper · level 1 · ran · our draft was wrong · a089868d27926865

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2402.12656") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Mixture-of-ExpertsMulti-Task Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections