Papers › Temporally Disentangled Representation Learning

Temporally Disentangled Representation Learning

24 Oct 2022arXiv:2210.13647archive 2025-07-28

Weiran Yao, Guangyi Chen, Kun Zhang

Recently in the field of unsupervised representation learning, strong identifiability results for disentanglement of causally-related latent variables have been established by exploiting certain side information, such as class labels, in addition to independence. However, most existing work is constrained by functional form assumptions such as independent sources or further with linear transitions, and distribution assumptions such as stationary, exponential family distribution. It is unknown whether the underlying latent variables and their causal relations are identifiable if they have arbitrary, nonparametric causal influences in between. In this work, we establish the identifiability theories of nonparametric latent causal processes from their nonlinear mixtures under fixed temporal causal influences and analyze how distribution changes can further benefit the disentanglement. We propose TDRL, a principled framework to recover time-delayed latent causal variables and identify their relations from measured sequential data under stationary environments and under different distribution shifts. Specifically, the framework can factorize unknown distribution shifts into transition distribution changes under fixed and time-varying latent causal relations, and under observation changes in observation. Through experiments, we show that time-delayed latent causal influences are reliably identified and that our approach considerably outperforms existing baselines that do not correctly exploit this modular representation of changes. Our code is available at: https://github.com/weirayao/tdrl.

PaperPDFCode 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 17 code samples harvested from 1 repository linked to this paper: 10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 17 samples from 1 repository, 10 ran (6 with no instrument failure; 4 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

weirayao/tdrl found in paper text by SyntologySyntology: 17 samples, 10 ran (4 instrument-failed) · 7 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

17 samples harvested: 10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
2ran; the contract check could not run
5ran
7unverified

Licence: 0 of the 17 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 weirayao/tdrl. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

weirayao/tdrl found in paper text by Syntology 17 samples, 10 ran (4 instrument-failed) · 7 unverified
BetaVAE_MLP LiLY/modules/modular.py ran · metamorphic tier: deterministic MIT (permissive) · de30ee3689394b09 · report fixture: returned BetaVAE_MLP · level recorded 2026-09-22
GroupLinearLayer LiLY/modules/modular.py ran · metamorphic tier: deterministic MIT (permissive) · 3afb21c8fdb93144 · report fixture: returned GroupLinearLayer · level recorded 2026-09-22
MBDTransitionPrior LiLY/modules/modular.py ran · metamorphic tier: deterministic MIT (permissive) · 99f55689f9c969b1 · report fixture: returned MBDTransitionPrior · level recorded 2026-09-22
NLayerLeakyMLP LiLY/modules/modular.py ran · metamorphic tier: deterministic MIT (permissive) · c4c2e657dc649aae · report fixture: returned NLayerLeakyMLP · level recorded 2026-09-22
NPChangeTransitionPrior LiLY/modules/modular.py ran · metamorphic tier: deterministic MIT (permissive) · 59237073932bbf22 · report fixture: returned NPChangeTransitionPrior · level recorded 2026-09-22
_calculate_knots LiLY/modules/modular.py ran · our draft was wrong fingerprinted MIT (permissive) · 09afbd64a67309fa · report fixture: signature lengths:Tensor/2/float, lower:float/0/float, upper:float/0/float · returned tuple · level recorded 2026-09-22
_monotonic_rational_spline LiLY/modules/modular.py ran; the contract check could not run (RAISES) MIT (permissive) · 98886c9bc0d385ae · report fixture: signature inputs:Tensor/2/float, widths:Tensor/3/float, heights:Tensor/3/float, derivatives:Tensor/3/float, lambdas:Tensor/3/float, inverse:bool/0/bool, bound:float/0/float, min_bin_width:float/0/float, min_bin_height:float/0/float, min_derivative:float/0/float, min_lambda:float/0/float, eps:float/0/float · returned tuple · level recorded 2026-09-22
_searchsorted LiLY/modules/modular.py ran · honoured contract MIT (permissive) · bb9c599734501473 · report fixture: signature sorted_sequence:Tensor/1/float, values:Tensor/2/float · returned Tensor · level recorded 2026-09-22
_select_bins LiLY/modules/modular.py ran; the contract check could not run (RAISES) MIT (permissive) · 48a69d3feffa4d35 · report fixture: signature x:Tensor/3/float, idx:Tensor/3/int · returned Tensor · level recorded 2026-09-22
make_cost_matrix in 8 papers LiLY/modules/modular.py ran · our draft was wrong MIT (permissive) · 60f32cea809132df · report fixture: signature profit_matrix:list/1/list, inversion_function:callable/0/? · returned list · level recorded 2026-09-22
ComponentWiseCondSpline LiLY/modules/modular.py unverified MIT (permissive) · 0058b6a47fe9f194 · report
ModularShifts LiLY/modules/modular.py unverified MIT (permissive) · 295b9fa436b63536 · report
Munkres LiLY/modules/modular.py unverified MIT (permissive) · 490d0594e6f6579c · report
_construct_nn LiLY/modules/modular.py unverified MIT (permissive) · e09f312815d1ee82 · report
compute_mcc LiLY/modules/modular.py unverified MIT (permissive) · 0b6abb112159adb6 · report
correlation in 16 papers LiLY/modules/modular.py unverified MIT (permissive) · 228dbb5491c93115 · report
kaiming_init in 9 papers LiLY/modules/modular.py unverified MIT (permissive) · a18c3595f7425f34 · 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 TDRL (graph method: TDRL). 18 bricks; individually on a fixture: 11 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. ModularShifts entry · level 0 · unverified · 295b9fa436b63536
  2. BetaVAE_MLP helper · level 1 · ran · de30ee3689394b09
  3. ComponentWiseCondSpline helper · level 0 · unverified · 0058b6a47fe9f194
  4. MBDTransitionPrior helper · level 1 · ran · 99f55689f9c969b1
  5. NPChangeTransitionPrior helper · level 1 · ran · 59237073932bbf22
  6. compute_mcc helper · level 0 · unverified · 0b6abb112159adb6
  7. correlation helper · level 0 · unverified · 228dbb5491c93115
  8. kaiming_init helper · level 0 · unverified · a18c3595f7425f34
  9. reparametrize helper · level 1 · ran · honoured contract · 863fc64cd51264f0
  10. _construct_nn helper · level 0 · unverified · e09f312815d1ee82
  11. _monotonic_rational_spline helper · level 1 · ran; the contract check could not run (RAISES) · 98886c9bc0d385ae
  12. GroupLinearLayer model · level 1 · ran · 3afb21c8fdb93144
  13. NLayerLeakyMLP helper · level 1 · ran · c4c2e657dc649aae
  14. Munkres helper · level 0 · unverified · 490d0594e6f6579c
  15. _calculate_knots helper · level 1 · ran · our draft was wrong · 09afbd64a67309fa
  16. _searchsorted helper · level 1 · ran · honoured contract · bb9c599734501473
  17. _select_bins helper · level 1 · ran; the contract check could not run (RAISES) · 48a69d3feffa4d35
  18. make_cost_matrix helper · level 1 · ran · our draft was wrong · 60f32cea809132df

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="2210.13647") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DisentanglementRepresentation Learning

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