Papers › High-Performance Temporal Reversible Spiking Neural Networks with O(L) Training Memory...

High-Performance Temporal Reversible Spiking Neural Networks with O(L) Training Memory and O(1) Inference Cost

26 May 2024arXiv:2405.16466archive 2025-07-28

Jiakui Hu, Man Yao, Xuerui Qiu, Yuhong Chou, Yuxuan Cai, Ning Qiao, Yonghong Tian, Bo Xu, Guoqi Li

Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods cannot simultaneously solve both training and inference dilemmas. This work proposes a novel Temporal Reversible architecture for SNNs (T-RevSNN) to jointly address the training and inference challenges by altering the forward propagation of SNNs. We turn off the temporal dynamics of most spiking neurons and design multi-level temporal reversible interactions at temporal turn-on spiking neurons, resulting in a O(L) training memory. Combined with the temporal reversible nature, we redesign the input encoding and network organization of SNNs to achieve O(1) inference energy cost. Then, we finely adjust the internal units and residual connections of the basic SNN block to ensure the effectiveness of sparse temporal information interaction. T-RevSNN achieves excellent accuracy on ImageNet, while the memory efficiency, training time acceleration, and inference energy efficiency can be significantly improved by 8.6 ×, 2.0 ×, and 1.6 ×, respectively. This work is expected to break the technical bottleneck of significantly increasing memory cost and training time for large-scale SNNs while maintaining high performance and low inference energy cost. Source code and models are available at: https://github.com/BICLab/T-RevSNN.

PaperPDFCodeCode 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

Syntology 19 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (9 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 4 ran (4 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

biclab/t-revsnn officialmentioned in paperpytorchSyntology: 15 samples, 13 ran (4 instrument-failed) · 2 unverified report
MindSpore-scientific-2/code-7 mindsporeSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 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

19 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 2 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
1ran · violated contract
4ran · our draft was wrong
11ran
2unverified

Licence: 15 of the 19 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 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”. “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.

biclab/t-revsnn official repository 15 samples, 13 ran (4 instrument-failed) · 2 unverified
TET_loss in 7 papers loss.py ran no licence file found · pointer only · a71accca7675fc44 · report fixture: signature outputs:Tensor/3/float, labels:Tensor/2/float, criterion:callable/0/?, means:float/0/float, lamb:float/0/float · returned Tensor · level recorded 2026-09-24
build_scheduler in 56 papers lr_scheduler.py ran no licence file found · pointer only · c9aba121df4c6d52 · report fixture: signature config:MockConfig/0/?, optimizer:SGD/0/? · returned CosLRScheduler · level recorded 2026-09-24
calc_firing_rate main_no_decoder.py ran no licence file found · pointer only · 30efe3fef88ef14c · report fixture: signature s_dict:dict/0/?, fr_dict:dict/0/?, idx:int/0/int, t:int/0/int · returned dict · level recorded 2026-09-24
calc_non_zero_rate main_no_decoder.py ran no licence file found · pointer only · d61a821f2b84fe36 · report fixture: signature s_dict:dict/0/?, nz_dict:dict/0/?, idx:int/0/int, t:int/0/int · returned dict · level recorded 2026-09-24
check_keywords_in_name in 32 papers optimizer.py ran · violated contract no licence file found · pointer only · b0a5beb34716d5a6 · report fixture: signature name:str/0/str, keywords:tuple/1/str · returned bool · level recorded 2026-09-25
compound_loss_only_cls loss.py ran no licence file found · pointer only · 85558ca537762448 · report fixture: signature output_label:list/1/Tensor, targets:Tensor/1/int, criterion_ce:callable/0/?, epoch:int/0/int · returned Tensor · level recorded 2026-09-24
create_logger in 172 papers logger.py ran · our draft was wrong no licence file found · pointer only · 80450600f7f09b0a · report fixture: signature output_dir:str/0/str, dist_rank:int/0/int, name:str/0/str · returned Logger · level recorded 2026-09-25
detach_and_grad models/rev_function.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3227c202c2b3ebf1 · report fixture: signature inputs:tuple/1/Tensor · returned tuple · level recorded 2026-09-24
get_cpu_and_gpu_states models/rev_function.py ran · our draft was wrong no licence file found · pointer only · c2a073f0eb31bd73 · report fixture: signature gpu_devices:list/1/empty · returned tuple · level recorded 2026-09-24
get_grad_norm in 45 papers utils.py ran · honoured contract no licence file found · pointer only · eec1e7cba51d5e8e · report fixture: signature parameters:list/1/Tensor, norm_type:int/0/int · returned float · level recorded 2026-09-22
load_checkpoint in 277 papers utils.py ran no licence file found · pointer only · d429b6a417929c36 · report fixture: signature config:Config/0/?, model:callable/0/?, optimizer:SGD/0/?, logger:Logger/0/?, model_ema:ModelEMA/0/? · returned float · level recorded 2026-09-24
set_weight_decay in 32 papers optimizer.py ran no licence file found · pointer only · 5dd42a7ce2cea5bd · report fixture: signature model:callable/0/?, skip_list:tuple/1/str, skip_keywords:tuple/1/str · returned list · level recorded 2026-09-24
unitwise_norm utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 670bc2732a11c7eb · report fixture: signature x:Tensor/2/float, norm_type:float/0/float · returned Tensor · level recorded 2026-09-24
get_config in 203 papers config.py unverified no licence file found · pointer only · 547f21f5227890b7 · report
get_gpu_states models/rev_function.py unverified no licence file found · pointer only · 09909a0053973029 · report
MindSpore-scientific-2/code-7 community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
get_padding in 84 papers ms_spike_modules.py ran fingerprinted Apache-2.0 (permissive) · e2a6feec71c8cf83 · report fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-24
laplacians pointdpi/utils_for_matching_dtinet.py ran fingerprinted Apache-2.0 (permissive) · a41e4bcb54a4b5d2 · report fixture: signature A:ndarray/2/float · returned ndarray · level recorded 2026-09-24
line_normalize pointdpi/utils_for_matching_dtinet.py ran fingerprinted Apache-2.0 (permissive) · 038548fc8980d84c · report fixture: signature A:ndarray/2/float · returned ndarray · level recorded 2026-09-24
max_min_normalize pointdpi/utils_for_matching_dtinet.py ran fingerprinted Apache-2.0 (permissive) · ec5063b857ea5fa8 · report fixture: signature a:ndarray/2/float · returned ndarray · level recorded 2026-09-24

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SNN

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