Papers › PoNet: Pooling Network for Efficient Token Mixing in Long Sequences

PoNet: Pooling Network for Efficient Token Mixing in Long Sequences

6 Oct 2021ICLR 2022 4arXiv:2110.02442archive 2025-07-28

Chao-Hong Tan, Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Zhen-Hua Ling

Transformer-based models have achieved great success in various NLP, vision, and speech tasks. However, the core of Transformer, the self-attention mechanism, has a quadratic time and memory complexity with respect to the sequence length, which hinders applications of Transformer-based models to long sequences. Many approaches have been proposed to mitigate this problem, such as sparse attention mechanisms, low-rank matrix approximations and scalable kernels, and token mixing alternatives to self-attention. We propose a novel Pooling Network (PoNet) for token mixing in long sequences with linear complexity. We design multi-granularity pooling and pooling fusion to capture different levels of contextual information and combine their interactions with tokens. On the Long Range Arena benchmark, PoNet significantly outperforms Transformer and achieves competitive accuracy, while being only slightly slower than the fastest model, FNet, across all sequence lengths measured on GPUs. We also conduct systematic studies on the transfer learning capability of PoNet and observe that PoNet achieves 95.7% of the accuracy of BERT on the GLUE benchmark, outperforming FNet by 4.5% relative. Comprehensive ablation analysis demonstrates effectiveness of the designed multi-granularity pooling and pooling fusion for token mixing in long sequences and efficacy of the designed pre-training tasks for PoNet to learn transferable contextualized language representations.

PaperPDFConference PDFCodeCode Syntology ran

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

The archive's official repository (lxchtan/ponet) was not harvested; the 11 samples below come from 1 repository the archive does not mark official.

Syntology 11 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: found in paper text by Syntology: 11 samples from 1 repository, 11 ran (11 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lxchtan/ponet officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested 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

11 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran

Licence: 11 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from erksch/fnet-pytorch. “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”. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

erksch/fnet-pytorch found in paper text by Syntology 11 samples, 11 ran (0 instrument-failed) · 0 unverified
concat_lines_until_max training/data_preparation.py ran MIT recorded; this copy not marked cleared · pointer only · 7a5d3cdb6ed5812d · report fixture: signature lines:list/1/str, max_len:int/0/int · returned list · level recorded 2026-09-24
convert_encoder convert_jax_checkpoint.py ran MIT recorded; this copy not marked cleared · pointer only · aed785e96913727a · report fixture: signature target:callable/0/?, jax_tree:dict/0/? · returned TargetModel · level recorded 2026-09-24
get_config_from_statedict fnet.py ran MIT recorded; this copy not marked cleared · pointer only · eb505d6b0c682ecf · report fixture: signature state_dict:dict/0/?, fourier_type:str/0/str, pad_token_id:int/0/int, layer_norm_eps:float/0/float, dropout_rate:float/0/float · returned dict · level recorded 2026-09-24
get_hits in 6 papers training/pretraining.py ran MIT recorded; this copy not marked cleared · pointer only · b4a5c940a3986725 · report fixture: signature batch:dict/0/?, pred:dict/0/? · returned dict · level recorded 2026-09-24
get_input in 20 papers verify_conversion.py ran MIT recorded; this copy not marked cleared · pointer only · 5eccccd396511ac2 · report fixture: signature tokenizer:MockTokenizer/0/?, seq_len:int/0/int · returned tuple · level recorded 2026-09-24
get_loss in 107 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
training/pretraining.py ran MIT recorded; this copy not marked cleared · pointer only · 8f2cc35ebde28dfb · report fixture: signature batch:dict/0/?, pred:dict/0/?, mlm_criterion:callable/0/?, nsp_criterion:callable/0/? · returned dict · level recorded 2026-09-24
jax_init_params verify_conversion.py ran MIT recorded; this copy not marked cleared · pointer only · afb6a62075edd740 · report fixture: signature model:MinimalJaxModel/0/?, key:ArrayImpl/1/int, config:Config/0/? · returned dict · level recorded 2026-09-24
load_config in 389 papers training/load_config.py ran MIT recorded; this copy not marked cleared · pointer only · b25c0106e8a92528 · report fixture: signature config_path:str/0/str · returned dict · level recorded 2026-09-24
load_jax_checkpoint convert_jax_checkpoint.py ran MIT recorded; this copy not marked cleared · pointer only · aafd51fb0aa641e2 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
samples_to_batch training/data_preparation.py ran MIT recorded; this copy not marked cleared · pointer only · 8b2a4406d6a846ad · report fixture: signature samples:list/1/dict, device:str/0/str · returned dict · level recorded 2026-09-24
to_torch in 53 papers
census: 5 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
convert_jax_checkpoint.py ran MIT recorded; this copy not marked cleared · pointer only · 7fb57f0edc23a95b · report fixture: signature arr:ndarray/2/float · returned Tensor · level recorded 2026-09-24

Tasks

Transfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerWeight DecayWordPiece

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