Papers › Classifier-guided Gradient Modulation for Enhanced Multimodal Learning

Classifier-guided Gradient Modulation for Enhanced Multimodal Learning

3 Nov 2024arXiv:2411.01409archive 2025-07-28

Zirun Guo, Tao Jin, Jingyuan Chen, Zhou Zhao

Multimodal learning has developed very fast in recent years. However, during the multimodal training process, the model tends to rely on only one modality based on which it could learn faster, thus leading to inadequate use of other modalities. Existing methods to balance the training process always have some limitations on the loss functions, optimizers and the number of modalities and only consider modulating the magnitude of the gradients while ignoring the directions of the gradients. To solve these problems, in this paper, we present a novel method to balance multimodal learning with Classifier-Guided Gradient Modulation (CGGM), considering both the magnitude and directions of the gradients. We conduct extensive experiments on four multimodal datasets: UPMC-Food 101, CMU-MOSI, IEMOCAP and BraTS 2021, covering classification, regression and segmentation tasks. The results show that CGGM outperforms all the baselines and other state-of-the-art methods consistently, demonstrating its effectiveness and versatility. Our code is available at https://github.com/zrguo/CGGM.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2411.01409")

Code

Syntology Ran 10 of 25 code samples harvested from 1 repository linked to this paper; 15 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 25 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zrguo/cggm officialmentioned in paperpytorchMIT 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

25 samples harvested; 10 ran; 2 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
1ran · fixture could not drive it
5ran
15unverified

Licence: 0 of the 25 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 zrguo/CGGM. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Linear zrguo/CGGM/modules/transformer.py official repository ran · our draft was wrong MIT (permissive) · 10865bbb99140edd · report
buffered_future_mask zrguo/CGGM/modules/transformer.py official repository ran · violated contract fingerprinted MIT (permissive) · 184a5eddedaf6a42 · report
cal_cos zrguo/cggm/src/foodtrain.py official repository ran MIT (permissive) · ed6f4e9e545f8f07 · report
eval_food zrguo/cggm/src/foodtrain.py official repository ran MIT (permissive) · d67ae69618e8f777 · report
fill_with_neg_inf zrguo/CGGM/modules/transformer.py official repository ran · honoured contract fingerprinted MIT (permissive) · 8f266b9d616de9b9 · report
make_positions zrguo/CGGM/modules/position_embedding.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 21958d540bd87a8c · report
train_eval_food zrguo/cggm/src/foodtrain.py official repository ran MIT (permissive) · b39cbc0e9aa13c48 · report
train_eval_iemo zrguo/cggm/src/foodtrain.py official repository ran MIT (permissive) · ad9faeb1beaacf40 · report
train_eval_senti zrguo/cggm/src/foodtrain.py official repository ran MIT (permissive) · 7b0ce64e017cea1a · report
weighted_accuracy zrguo/CGGM/src/eval_metrics.py official repository ran · honoured contract fingerprinted MIT (permissive) · 6d4da8365bb0f5d1 · report
Classifier zrguo/cggm/src/foodtrain.py official repository unverified MIT (permissive) · f70f65ad58a53350 · report
ClassifierGuided zrguo/cggm/src/foodtrain.py official repository unverified MIT (permissive) · f927307b92481f41 · report
FoodModel zrguo/cggm/src/foodtrain.py official repository unverified MIT (permissive) · 1cd046b456ad9f31 · report
ResNet101 zrguo/CGGM/models/segmodel.py official repository unverified MIT (permissive) · 6aa213f79f005ec4 · report
TransformerEncoder zrguo/cggm/src/foodtrain.py official repository unverified MIT (permissive) · 34ea1f3d71361140 · report
TransformerEncoderLayer zrguo/cggm/src/foodtrain.py official repository unverified MIT (permissive) · 3dfcc20147c77637 · report
augment_gaussian_noise zrguo/CGGM/datasets/BratsDataset.py official repository unverified MIT (permissive) · 1fe4d67c3bc4510b · report
build_aspp zrguo/CGGM/models/segmodel.py official repository unverified MIT (permissive) · 137ee892a73b5311 · report
build_decoder zrguo/CGGM/models/segmodel.py official repository unverified MIT (permissive) · 22ecd809e4d1de39 · report
cutout zrguo/CGGM/datasets/BratsDataset.py official repository unverified MIT (permissive) · 653ae4081b06cab6 · report
eval_senti zrguo/CGGM/src/eval_metrics.py official repository unverified MIT (permissive) · cae47ad9ef47ac82 · report
initiate zrguo/cggm/src/foodtrain.py official repository unverified MIT (permissive) · e2fe3744d6f3b381 · report
multiclass_acc zrguo/CGGM/src/eval_metrics.py official repository unverified MIT (permissive) · 65494cdd1508772e · report
train_model zrguo/cggm/src/foodtrain.py official repository unverified MIT (permissive) · 341db6e7ca441245 · report
train_model zrguo/CGGM/src/segtrain.py official repository unverified MIT (permissive) · 27a4ff497fab5848 · report

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