Papers › Vector Quantization Prompting for Continual Learning

Vector Quantization Prompting for Continual Learning

27 Oct 2024arXiv:2410.20444archive 2025-07-28

Li Jiao, Qiuxia Lai, Yu Li, Qiang Xu

Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that utilize a set of learnable parameters (i.e., prompts) to encode task knowledge, from which appropriate ones are selected to guide the fixed pre-trained model in generating features tailored to a certain task. However, existing methods rely on predicting prompt identities for prompt selection, where the identity prediction process cannot be optimized with task loss. This limitation leads to sub-optimal prompt selection and inadequate adaptation of pre-trained features for a specific task. Previous efforts have tried to address this by directly generating prompts from input queries instead of selecting from a set of candidates. However, these prompts are continuous, which lack sufficient abstraction for task knowledge representation, making them less effective for continual learning. To address these challenges, we propose VQ-Prompt, a prompt-based continual learning method that incorporates Vector Quantization (VQ) into end-to-end training of a set of discrete prompts. In this way, VQ-Prompt can optimize the prompt selection process with task loss and meanwhile achieve effective abstraction of task knowledge for continual learning. Extensive experiments show that VQ-Prompt outperforms state-of-the-art continual learning methods across a variety of benchmarks under the challenging class-incremental setting. The code is available at this https URL (https://github.com/jiaolifengmi/VQ-Prompt).

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 15 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 7 ran (2 with no instrument failure; 5 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. 1 of the 7 samples that ran has no recorded date.

jiaolifengmi/vq-prompt officialmentioned in paperpytorchMITSyntology: 15 samples, 7 ran (5 instrument-failed) · 8 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

15 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 8 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
4ran · our draft was wrong
1ran; the contract check could not run
1ran
8unverified

Licence: 1 of the 15 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 jiaolifengmi/vq-prompt. “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.

jiaolifengmi/vq-prompt official repository 15 samples, 7 ran (5 instrument-failed) · 8 unverified
build_cifar_transform dataloaders/utils.py ran · our draft was wrong MIT (permissive) · f83acd2eda10d232 · report fixture: signature is_train:bool/0/bool, input_size:int/0/int · returned Compose · level recorded 2026-09-26
build_transform in 170 papers dataloaders/utils.py ran · our draft was wrong MIT (permissive) · aa97aea5d1c8ffb8 · report fixture: signature is_train:bool/0/bool, input_size:int/0/int · returned Compose · level recorded 2026-09-26
get_transform in 75 papers dataloaders/utils.py ran MIT (permissive) · b682650616ae4f66 · report fixture: signature dataset:str/0/str, phase:str/0/str, aug:bool/0/bool, resize_imnet:bool/0/bool · returned Compose · level recorded 2026-09-26
interpolate_pos_embed in 59 papers models/vit.py ran · our draft was wrong MIT (permissive) · c6ec173f19f5c34d · report fixture: signature pos_embed_checkpoint:Tensor/3/float, visual_encoder:callable/0/? · returned Tensor · level recorded, date not recorded
ortho_penalty in 5 papers models/zoo.py ran; the contract check could not run (RAISES) MIT (permissive) · a763dc6f8d5d1498 · report fixture: returned Tensor · level recorded 2026-09-22
parse_txt dataloaders/dataloader.py ran · our draft was wrong MIT (permissive) · cdf0934ebf6a93cd · report fixture: signature txt_file:str/0/str · returned tuple · level recorded 2026-09-26
tensor_prompt in 8 papers models/zoo.py ran · honoured contract fingerprinted MIT (permissive) · 3f33843b601c8d4d · report fixture: signature a:int/0/int, b:int/0/int, c:NoneType/0/?, ortho:bool/0/bool · returned Parameter · level recorded 2026-09-22
CosineSchedulerIter learners/prompt.py unverified MIT (permissive) · fe7f9a1f5cd3c429 · report
NormalNN learners/prompt.py unverified MIT (permissive) · a447093382d3a413 · report
Prompt in 17 papers learners/prompt.py unverified MIT (permissive) · 677d8160bcc4ebc6 · report
VQPrompt learners/prompt.py unverified MIT (permissive) · 6ffe4ffedcac064a · report
_LRSchedulerIter learners/prompt.py unverified MIT (permissive) · 23f35d8ff6184ceb · report
calc_forgetting utils/calc_forgetting.py unverified MIT (permissive) · 4e39da6c733f9f2c · report
jpg_image_to_array dataloaders/dataloader.py unverified MIT (permissive) here; the stored copy is pointer only · e1da3ea75e559fb9 · 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 VQ-Prompt (graph method: VQ-Prompt). 12 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. VQPrompt entry · level 0 · unverified · 6ffe4ffedcac064a
  2. Prompt model · level 0 · unverified · 677d8160bcc4ebc6
  3. CosineSchedule helper · level 1 · ran · fb5af0c577ee3e37
  4. CosineSchedulerIter helper · level 0 · unverified · fe7f9a1f5cd3c429
  5. NormalNN helper · level 0 · unverified · a447093382d3a413
  6. _LRScheduler helper · level 0 · unverified · 0da189d1706732b7
  7. _LRSchedulerIter helper · level 0 · unverified · 23f35d8ff6184ceb
  8. AverageMeter helper · level 1 · ran · fcca5441c56a56a7
  9. Timer helper · level 1 · ran · a734a8b4d53236df
  10. accumulate_acc helper · level 1 · ran · our draft was wrong · 58afbcc75976684a
  11. weight_reset helper · level 0 · unverified · 484c4459ced99c20
  12. accuracy helper · level 0 · unverified · 0c4bbcb160a04955

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="2410.20444") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continual LearningQuantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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