Papers › Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

16 Feb 2022ICLR 2022 4arXiv:2202.07857archive 2025-07-28

Enyan Dai, Jie Chen

Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks. Detecting anomalies for multiple time series, however, is a challenging subject, owing to the intricate interdependencies among the constituent series. We hypothesize that anomalies occur in low density regions of a distribution and explore the use of normalizing flows for unsupervised anomaly detection, because of their superior quality in density estimation. Moreover, we propose a novel flow model by imposing a Bayesian network among constituent series. A Bayesian network is a directed acyclic graph (DAG) that models causal relationships; it factorizes the joint probability of the series into the product of easy-to-evaluate conditional probabilities. We call such a graph-augmented normalizing flow approach GANF and propose joint estimation of the DAG with flow parameters. We conduct extensive experiments on real-world datasets and demonstrate the effectiveness of GANF for density estimation, anomaly detection, and identification of time series distribution drift.

PaperPDFConference PDFCodeCode 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 24 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 9 samples from 1 repository, 3 ran (3 with no instrument failure; 0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

enyandai/ganf officialmentioned in paperpytorchSyntology: 10 samples, 7 ran (1 instrument-failed) · 3 unverified report
D3-AI/Orion mentioned on GitHubtfMITSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
signals-dev/Orion mentioned on GitHubtfMITSyntology: not harvested report
sintel-dev/orion mentioned on GitHubtfMITSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

24 samples harvested: 13 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 11 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
1ran · our draft was wrong
11ran
11unverified

Licence: 11 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 3 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.

enyandai/ganf official repository 10 samples, 7 ran (1 instrument-failed) · 3 unverified
BatchNorm in 19 papers models/GANF.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 161cda5cabbb68c3 · report fixture: returned BatchNorm · level recorded 2026-09-22
GNN in 23 papers models/GANF.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9115fcfda4b932e3 · report fixture: returned GNN · level recorded 2026-09-22
LinearMaskedCoupling models/GANF.py ran · metamorphic tier: deterministic no licence file found · pointer only · 892f63ab6c5f2f84 · report fixture: returned LinearMaskedCoupling · level recorded 2026-09-22
MADE in 7 papers models/GANF.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · b5885c7b74843b05 · report fixture: returned MADE · level recorded 2026-09-22
MaskedLinear in 9 papers models/GANF.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 466de1ea4db58ebc · report fixture: returned MaskedLinear · level recorded 2026-09-22
RealNVP in 5 papers models/GANF.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0b745b7baaf925c0 · report fixture: returned RealNVP · level recorded 2026-09-22
create_masks in 17 papers models/GANF.py ran · our draft was wrong fingerprinted no licence file found · pointer only · e1243b39051334f9 · report fixture: signature input_size:int/0/int, hidden_size:int/0/int, n_hidden:int/0/int, input_order:str/0/str, input_degrees:NoneType/0/? · returned tuple · level recorded 2026-09-22
FlowSequential models/GANF.py unverified no licence file found · pointer only · 213315d48b01e0a7 · report
GANF models/GANF.py unverified no licence file found · pointer only · 2a25b017dff45e00 · report
MAF models/GANF.py unverified no licence file found · pointer only · 02e105c797e3990c · report
D3-AI/Orion community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
download in 53 papers orion/data.py ran MIT (permissive) · b1b2e280183a2f78 · report fixture: returned DataFrame · level recorded 2026-09-24
format_csv orion/data.py ran MIT (permissive) · fc4f07905e94f225 · report fixture: signature df:DataFrame/0/?, timestamp_column:int/0/int, value_columns:list/1/int · returned DataFrame · level recorded 2026-09-24
get_f1_scores orion/results.py ran MIT (permissive) · 1267f9f70dc9e57e · report fixture: signature results:DataFrame/0/? · returned DataFrame · level recorded 2026-09-24
get_summary_page orion/results.py unverified MIT (permissive) · 6601ccd471fa6c41 · report
load_csv in 32 papers orion/data.py unverified MIT (permissive) · 04aff2c366db2eed · report
khalooei/ALOCC-CVPR2018 found in paper text by Syntology 9 samples, 3 ran (0 instrument-failed) · 6 unverified
conv_out_size_same in 7 papers utils.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 40125e1efb67fa92 · report fixture: signature size:int/0/int, stride:int/0/int · returned int · level recorded 2026-09-22
get_noisy_data kh_tools.py ran MIT (permissive) · 489e2c5f7ad2b380 · report fixture: signature data:list/1/ndarray · returned ndarray · level recorded 2026-09-24
read_dataset_image_path kh_tools.py ran fingerprinted MIT (permissive) · 3dff213b8ae5a2d4 · report fixture: signature s_dataset_url:str/0/str, n_number_count:NoneType/0/? · returned list · level recorded 2026-09-24
conv2d in 119 papers ops.py unverified MIT (permissive) · f0cb37d52c4b56e2 · report
conv_cond_concat in 10 papers ops.py unverified MIT (permissive) · 97a17fbee43a92bd · report
deconv2d in 15 papers ops.py unverified MIT (permissive) · f43eeb47efdaf9c4 · report
get_image in 52 papers utils.py unverified MIT (permissive) · a0b95d6b4e00d081 · report
get_image_Slicization utils.py unverified MIT (permissive) · 0ac44cb4f2a04c3e · report
read_image_w_noise kh_tools.py unverified MIT (permissive) · 4c27080e85e975e7 · 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 GANF (graph method: GANF). 10 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. GANF entry · level 0 · unverified · 2a25b017dff45e00
  2. GNN model · level 1 · ran · 9115fcfda4b932e3
  3. MAF model · level 0 · unverified · 02e105c797e3990c
  4. RealNVP model · level 1 · ran · 0b745b7baaf925c0
  5. BatchNorm helper · level 1 · ran · 161cda5cabbb68c3
  6. FlowSequential helper · level 0 · unverified · 213315d48b01e0a7
  7. MADE helper · level 1 · ran · b5885c7b74843b05
  8. LinearMaskedCoupling helper · level 1 · ran · 892f63ab6c5f2f84
  9. MaskedLinear helper · level 1 · ran · 466de1ea4db58ebc
  10. create_masks helper · level 1 · ran · our draft was wrong · e1243b39051334f9

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="2202.07857") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Anomaly DetectionDensity EstimationTime SeriesTime Series AnalysisUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection voraus-AD GANF Avg. Detection AUROC 79.9 #3 of 3 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

Normalizing Flows

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