Papers › Learning Associative Inference Using Fast Weight Memory

Learning Associative Inference Using Fast Weight Memory

16 Nov 2020ICLR 2021 1arXiv:2011.07831archive 2025-07-28

Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber

Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. To this end, we augment the LSTM model with an associative memory, dubbed Fast Weight Memory (FWM). Through differentiable operations at every step of a given input sequence, the LSTM updates and maintains compositional associations stored in the rapidly changing FWM weights. Our model is trained end-to-end by gradient descent and yields excellent performance on compositional language reasoning problems, meta-reinforcement-learning for POMDPs, and small-scale word-level language modelling.

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="2011.07831")

Code

Syntology Ran 2 of 3 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · honoured contract.

By repository: official repository: 3 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.

ischlag/Fast-Weight-Memory-public officialmentioned in paperpytorch 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

3 samples harvested; 2 ran; 2 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1unverified

Licence: 0 of the 3 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 ischlag/Fast-Weight-Memory-public. “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.

generate_graphs ischlag/Fast-Weight-Memory-public/metaRL/train_agent.py official repository ran · honoured contract MIT (permissive) · 924d55faa0c5cfd4 · report
sample_adjacency_matrix ischlag/Fast-Weight-Memory-public/metaRL/train_agent.py official repository ran · honoured contract MIT (permissive) · 05cbde8c37b9643f · report
run_episode ischlag/Fast-Weight-Memory-public/metaRL/train_agent.py official repository unverified MIT (permissive) · 83dc00c2fe9d0ac2 · report

Tasks

Language ModellingMeta Reinforcement LearningQuestion AnsweringReinforcement Learning (RL)reinforcement-learning

Datasets

Introduced by this paper, per the archive.

catbAbI LM-modecatbAbI QA-mode

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling Penn Treebank (Word Level) AWD-FWM Schlag et al. (2020) Params 24M #21 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) AWD-FWM Schlag et al. (2020) Test perplexity 54.48 #21 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) AWD-FWM Schlag et al. (2020) Validation perplexity 56.76 #21 of 43 Archive leaderboard report
Language Modelling WikiText-2 AWD-FWM Schlag et al. (2020) Number of params 37M #27 of 38 Archive leaderboard report
Language Modelling WikiText-2 AWD-FWM Schlag et al. (2020) Test perplexity 61.65 #27 of 38 Archive leaderboard report
Language Modelling WikiText-2 AWD-FWM Schlag et al. (2020) Validation perplexity 54.48 #27 of 38 Archive leaderboard report
Question Answering catbAbI LM-mode Fast Weight Memory Accuracy (mean) 93.04% #1 of 4 Archive leaderboard report
Question Answering catbAbI LM-mode AWD-Transformer XL Accuracy (mean) 90.23% #2 of 4 Archive leaderboard report
Question Answering catbAbI LM-mode AWD-LSTM Accuracy (mean) 80.15% #3 of 4 Archive leaderboard report
Question Answering catbAbI LM-mode Metalearned Neural Memory (plastic) Accuracy (mean) 69.3% #4 of 4 Archive leaderboard report
Question Answering catbAbI QA-mode Fast Weight Memory 1:1 Accuracy 96.75% #1 of 4 Archive leaderboard report
Question Answering catbAbI QA-mode Metalearned Neural Memory (plastic) 1:1 Accuracy 88.97% #2 of 4 Archive leaderboard report
Question Answering catbAbI QA-mode AWD-Transformer XL 1:1 Accuracy 87.66% #3 of 4 Archive leaderboard report
Question Answering catbAbI QA-mode AWD-LSTM 1:1 Accuracy 80.88% #4 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LSTMSigmoid ActivationTanh Activation

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