Papers › An Information Criterion for Controlled Disentanglement of Multimodal Data

An Information Criterion for Controlled Disentanglement of Multimodal Data

31 Oct 2024arXiv:2410.23996archive 2025-07-28

Chenyu Wang, Sharut Gupta, Xinyi Zhang, Sana Tonekaboni, Stefanie Jegelka, Tommi Jaakkola, Caroline Uhler

Multimodal representation learning seeks to relate and decompose information inherent in multiple modalities. By disentangling modality-specific information from information that is shared across modalities, we can improve interpretability and robustness and enable downstream tasks such as the generation of counterfactual outcomes. Separating the two types of information is challenging since they are often deeply entangled in many real-world applications. We propose Disentangled Self-Supervised Learning (DisentangledSSL), a novel self-supervised approach for learning disentangled representations. We present a comprehensive analysis of the optimality of each disentangled representation, particularly focusing on the scenario not covered in prior work where the so-called Minimum Necessary Information (MNI) point is not attainable. We demonstrate that DisentangledSSL successfully learns shared and modality-specific features on multiple synthetic and real-world datasets and consistently outperforms baselines on various downstream tasks, including prediction tasks for vision-language data, as well as molecule-phenotype retrieval tasks for biological data. The code is available at https://github.com/uhlerlab/DisentangledSSL.

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="2410.23996")

Code

Syntology Ran 8 of 26 code samples harvested from 1 repository linked to this paper; 18 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 26 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

uhlerlab/disentangledssl officialmentioned in papermentioned on GitHubpytorch 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

26 samples harvested; 8 ran; 0 honoured the contract we drafted; 18 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.

1ran · violated contract
1ran · our draft was wrong
2ran · fixture could not drive it
4ran
18unverified

Licence: 26 of the 26 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 uhlerlab/disentangledssl. “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.

AverageMeter uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository ran no licence file found · pointer only · 2a32b32bce61522c · report
ExponentialScheduler uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository ran no licence file found · pointer only · ff19362702b1f667 · report
LinearScheduler uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository ran no licence file found · pointer only · 97f933c8a55eb30f · report
Scheduler uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository ran no licence file found · pointer only · 3d40078d21ff70f7 · report
augment_data uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · fbaeedfcd82946ff · report
noise uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository ran · fixture could not drive it no licence file found · pointer only · d36953754afe8bd1 · report
random_drop uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 63022628853372a0 · report
str2bool uhlerlab/DisentangledSSL/synthetic_task/utils.py official repository ran · violated contract no licence file found · pointer only · 7c508037b40522af · report
JointDisenModel uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository unverified no licence file found · pointer only · bf7d4adba9989eda · report
batched_kldiv uhlerlab/DisentangledSSL/synthetic_task/losses.py official repository unverified no licence file found · pointer only · efddfa5f121e2841 · report
generate_data uhlerlab/DisentangledSSL/synthetic_task/dataset.py official repository unverified no licence file found · pointer only · f14b06907824c231 · report
initialize_weights uhlerlab/DisentangledSSL/synthetic_task/utils.py official repository unverified no licence file found · pointer only · 719fd1b978756582 · report
kl_divergence uhlerlab/DisentangledSSL/synthetic_task/losses.py official repository unverified no licence file found · pointer only · 28bcb2a124a000e4 · report
kl_vmf uhlerlab/DisentangledSSL/synthetic_task/losses.py official repository unverified no licence file found · pointer only · a51b6640a4ee9c8f · report
linearprobe uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository unverified no licence file found · pointer only · 00a23f6002d66b81 · report
mlp_head uhlerlab/DisentangledSSL/synthetic_task/algorithms.py official repository unverified no licence file found · pointer only · d800311dbc7d173c · report
print_row uhlerlab/disentangledssl/synthetic_task/algorithms.py official repository unverified no licence file found · pointer only · d7b63020c31d1627 · report
swap uhlerlab/DisentangledSSL/synthetic_task/dataset.py official repository unverified no licence file found · pointer only · 331078cd636b37a6 · report
train_mp uhlerlab/DisentangledSSL/synthetic_task/step1disen.py official repository unverified no licence file found · pointer only · fefda0a10805f22f · report
train_mp_dmvae uhlerlab/DisentangledSSL/synthetic_task/dmvae_mp.py official repository unverified no licence file found · pointer only · 5853242ad4773a37 · report
train_mp_focal uhlerlab/DisentangledSSL/synthetic_task/focal_mp.py official repository unverified no licence file found · pointer only · facf2bd1be8c81b5 · report
train_mp_joint uhlerlab/DisentangledSSL/synthetic_task/jointdisen_mp.py official repository unverified no licence file found · pointer only · e1f3a88ed0708b29 · report
train_step2 uhlerlab/DisentangledSSL/synthetic_task/step2disen.py official repository unverified no licence file found · pointer only · c78509e278339e80 · report
wrapper_train_mp uhlerlab/DisentangledSSL/synthetic_task/dmvae_mp.py official repository unverified no licence file found · pointer only · f4b4d9a3a2ce5ac9 · report
wrapper_train_mp uhlerlab/DisentangledSSL/synthetic_task/focal_mp.py official repository unverified no licence file found · pointer only · dd127a5e6f4aaf63 · report
wrapper_train_mp uhlerlab/DisentangledSSL/synthetic_task/jointdisen_mp.py official repository unverified no licence file found · pointer only · b9e665d3b5e9509a · report

Tasks

DisentanglementRepresentation LearningSelf-Supervised Learning

1 archive task tag without a task page not shown.

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