Papers › Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness

Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness

15 Jun 2021NeurIPS 2021 12arXiv:2106.08161archive 2025-07-28

Adam Foster, Árpi Vezér, Craig A Glastonbury, Páidí Creed, Sam Abujudeh, Aaron Sim

Learning meaningful representations of data that can address challenges such as batch effect correction and counterfactual inference is a central problem in many domains including computational biology. Adopting a Conditional VAE framework, we show that marginal independence between the representation and a condition variable plays a key role in both of these challenges. We propose the Contrastive Mixture of Posteriors (CoMP) method that uses a novel misalignment penalty defined in terms of mixtures of the variational posteriors to enforce this independence in latent space. We show that CoMP has attractive theoretical properties compared to previous approaches, and we prove counterfactual identifiability of CoMP under additional assumptions. We demonstrate state-of-the-art performance on a set of challenging tasks including aligning human tumour samples with cancer cell-lines, predicting transcriptome-level perturbation responses, and batch correction on single-cell RNA sequencing data. We also find parallels to fair representation learning and demonstrate that CoMP is competitive on a common task in the field.

PaperPDFConference PDFCodeCode 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="2106.08161")

Code

Syntology Ran 2 of 11 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

benevolentai/comp officialmentioned in papermentioned on GitHubpytorchMIT 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; 2 ran; 0 honoured the contract we drafted; 9 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 · our draft was wrong
1ran
9unverified

Licence: 0 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 benevolentai/comp. “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.

COMP benevolentai/comp/comp/pl/comp.py official repository ran MIT (permissive) · 4998f98685b3316e · report
pairwise_label_mask benevolentai/comp/comp/pl/comp.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 2b0137d425c7aa5a · report
calc_input_dims BenevolentAI/CoMP/comp/nn/utils.py official repository unverified MIT (permissive) · 668862ba4850b32a · report
compute_mmd BenevolentAI/CoMP/comp/metrics.py official repository unverified MIT (permissive) · bac34fce94abe980 · report
create_trainer BenevolentAI/CoMP/comp/pl/trainer.py official repository unverified MIT (permissive) · 559e347a0c942932 · report
get_umap_params BenevolentAI/CoMP/comp/metric_handlers.py official repository unverified MIT (permissive) · 465676336daf89fe · report
knn_metric BenevolentAI/CoMP/comp/metrics.py official repository unverified MIT (permissive) · b72cee35d4fa12ca · report
make_subset_penalty_v2 benevolentai/comp/comp/pl/comp.py official repository unverified MIT (permissive) · 3c7fe7b3de9552ce · report
mmd BenevolentAI/CoMP/comp/nn/loss.py official repository unverified MIT (permissive) · 6af69a37e94494a8 · report
predict BenevolentAI/CoMP/comp/metric_handlers.py official repository unverified MIT (permissive) · 90dbb0df2db2c052 · report
silhouette_coeff BenevolentAI/CoMP/comp/metrics.py official repository unverified MIT (permissive) · 71f33c01ffedd50d · report

Tasks

Counterfactual InferenceData IntegrationFairnessRepresentation 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