Papers › Fully Distributed, Flexible Compositional Visual Representations via Soft Tensor Products

Fully Distributed, Flexible Compositional Visual Representations via Soft Tensor Products

5 Dec 2024arXiv:2412.04671archive 2025-07-28

Bethia Sun, Maurice Pagnucco, Yang song

Since the inception of the classicalist vs. connectionist debate, it has been argued that the ability to systematically combine symbol-like entities into compositional representations is crucial for human intelligence. In connectionist systems, the field of disentanglement has gained prominence for its ability to produce explicitly compositional representations; however, it relies on a fundamentally symbolic, concatenative representation of compositional structure that clashes with the continuous, distributed foundations of deep learning. To resolve this tension, we extend Smolensky's Tensor Product Representation (TPR) and introduce Soft TPR, a representational form that encodes compositional structure in an inherently distributed, flexible manner, along with Soft TPR Autoencoder, a theoretically-principled architecture designed specifically to learn Soft TPRs. Comprehensive evaluations in the visual representation learning domain demonstrate that the Soft TPR framework consistently outperforms conventional disentanglement alternatives -- achieving state-of-the-art disentanglement, boosting representation learner convergence, and delivering superior sample efficiency and low-sample regime performance in downstream tasks. These findings highlight the promise of a distributed and flexible approach to representing compositional structure by potentially enhancing alignment with the core principles of deep learning over the conventional symbolic approach.

PaperPDFCodeCode Syntology ran

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 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 11 ran (7 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

gomb0c/soft_tpr officialmentioned in papermentioned on GitHubpytorchSyntology: 12 samples, 11 ran (4 instrument-failed) · 1 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
4ran · our draft was wrong
6ran
1unverified

Licence: 12 of the 12 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 gomb0c/soft_tpr. “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”. “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.

gomb0c/soft_tpr official repository 12 samples, 11 ran (4 instrument-failed) · 1 unverified
bce_recon_loss_fn src/repn_learners/soft_tpr_ae/optim/loss.py ran no licence file found · pointer only · 00ba486ea1f7537e · report fixture: signature x_hat:Tensor/2/float, x:Tensor/2/float, logging:bool/0/bool, logits:bool/0/bool · returned Tensor · level recorded 2026-09-25
gaussian_kls src/repn_learners/soft_tpr_ae/utils.py ran fingerprinted no licence file found · pointer only · 406c6e802e6ba500 · report fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float, mean:bool/0/bool · returned tuple · level recorded 2026-09-25
get_activation_name src/repn_learners/soft_tpr_ae/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a9ef158cd6f83f6d · report fixture: signature activation:str/0/str · returned str · level recorded 2026-09-25
get_most_recent_dir src/logger/load.py ran no licence file found · pointer only · 343bea31ec8dd2f5 · report fixture: signature save_dir:str/0/str, model_type:str/0/str, encoder_type:NoneType/0/? · returned tuple · level recorded 2026-09-25
get_n_layers src/repn_learners/soft_tpr_ae/utils.py ran no licence file found · pointer only · 0ed038365cbe2dc0 · report fixture: signature curr_w:int/0/int, desired_w:int/0/int, p:int/0/int, k_size:int/0/int, s:int/0/int, l:int/0/int · returned int · level recorded 2026-09-25
get_result_from_summary_json src/vis_results/plot_results_final-tpr_comparison.py ran · our draft was wrong no licence file found · pointer only · 4217eff3614e5a21 · report fixture: signature summary_json_path:str/0/str · returned dict · level recorded 2026-09-25
get_save_path in 5 papers src/logger/load.py ran no licence file found · pointer only · 76111b30fc874b16 · report fixture: signature args:Args/0/?, model_type:str/0/str · returned str · level recorded 2026-09-25
is_incorrect_run src/vis_results/plot_results_final-tpr_comparison.py ran · violated contract no licence file found · pointer only · 2445492633b2e3e7 · report fixture: signature load_dir:str/0/str · returned bool · level recorded 2026-09-25
mse_recon_loss_fn src/repn_learners/soft_tpr_ae/optim/loss.py ran no licence file found · pointer only · 58f2f3e8317316ec · report fixture: signature x_hat:Tensor/2/float, x:Tensor/2/float, logging:bool/0/bool, postprocessing:callable/0/? · returned Tensor · level recorded 2026-09-25
nearest_embed src/repn_learners/soft_tpr_ae/model/vq_vae.py ran · our draft was wrong no licence file found · pointer only · 34f0bd8890d57785 · report fixture: signature x:Tensor/3/float, emb:Tensor/2/float · returned tuple · level recorded 2026-09-22
nearest_embed src/repn_learners/soft_tpr_ae/model/nearest_embed.py ran · our draft was wrong no licence file found · pointer only · 663b284fc8ed7db2 · report fixture: signature x:Tensor/3/float, emb:Tensor/2/float · returned tuple · level recorded 2026-09-25
parse_results_from_wandb_logs src/vis_results/plot_results_final-tpr_comparison.py unverified no licence file found · pointer only · b2d4cc7bb63548ca · report

Tasks

DisentanglementRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

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