Papers › Unsupervised Learning of Equivariant Structure from Sequences

Unsupervised Learning of Equivariant Structure from Sequences

12 Oct 2022arXiv:2210.05972archive 2025-07-28

Takeru Miyato, Masanori Koyama, Kenji Fukumizu

In this study, we present meta-sequential prediction (MSP), an unsupervised framework to learn the symmetry from the time sequence of length at least three. Our method leverages the stationary property (e.g. constant velocity, constant acceleration) of the time sequence to learn the underlying equivariant structure of the dataset by simply training the encoder-decoder model to be able to predict the future observations. We will demonstrate that, with our framework, the hidden disentangled structure of the dataset naturally emerges as a by-product by applying simultaneous block-diagonalization to the transition operators in the latent space, the procedure which is commonly used in representation theory to decompose the feature-space based on the type of response to group actions. We will showcase our method from both empirical and theoretical perspectives. Our result suggests that finding a simple structured relation and learning a model with extrapolation capability are two sides of the same coin. The code is available at https://github.com/takerum/meta_sequential_prediction.

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="2210.05972")

Code

Syntology Ran 1 of 9 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 9 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

takerum/meta_sequential_prediction 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

9 samples harvested; 1 ran; 1 honoured the contract we drafted; 8 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 · honoured contract
8unverified

Licence: 0 of the 9 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 takerum/meta_sequential_prediction. “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.

positionalencoding2d takerum/meta_sequential_prediction/utils/emb2d.py official repository ran · honoured contract fingerprinted MIT (permissive) · 69664111108e8701 · report
conv_downsample takerum/meta_sequential_prediction/models/resblock.py official repository unverified MIT (permissive) · 38200f7b20908852 · report
get_index takerum/meta_sequential_prediction/datasets/small_norb.py official repository unverified MIT (permissive) · 342adeaf465617bd · report
get_index takerum/meta_sequential_prediction/datasets/three_dim_shapes.py official repository unverified MIT (permissive) · a57cd22c24266687 · report
make_diagonal takerum/meta_sequential_prediction/utils/laplacian.py official repository unverified MIT (permissive) · aeb211ca8536db16 · report
make_identity takerum/meta_sequential_prediction/utils/laplacian.py official repository unverified MIT (permissive) · ae6e56635c2b25df · report
make_identity_like takerum/meta_sequential_prediction/utils/laplacian.py official repository unverified MIT (permissive) · 5053b3c05376c313 · report
simclr takerum/meta_sequential_prediction/utils/clr.py official repository unverified MIT (permissive) · b11686650315f59e · report
upsample_conv takerum/meta_sequential_prediction/models/resblock.py official repository unverified MIT (permissive) · 0da12a1241154b15 · report

Tasks

Decoder

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