Papers › Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization

Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization

18 Nov 2023NeurIPS 2023 11arXiv:2311.11114archive 2025-07-28

Haonan Yuan, Qingyun Sun, Xingcheng Fu, Ziwei Zhang, Cheng Ji, Hao Peng, JianXin Li

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As the generation of dynamic graphs is heavily influenced by latent environments, investigating their impacts on the out-of-distribution (OOD) generalization is critical. However, it remains unexplored with the following two major challenges: (1) How to properly model and infer the complex environments on dynamic graphs with distribution shifts? (2) How to discover invariant patterns given inferred spatio-temporal environments? To solve these challenges, we propose a novel Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex coupled environments and exploiting spatio-temporal invariant patterns. Specifically, we first design the environment-aware EA-DGNN to model environments by multi-channel environments disentangling. Then, we propose an environment instantiation mechanism for environment diversification with inferred distributions. Finally, we discriminate spatio-temporal invariant patterns for out-of-distribution prediction by the invariant pattern recognition mechanism and perform fine-grained causal interventions node-wisely with a mixture of instantiated environment samples. Experiments on real-world and synthetic dynamic graph datasets demonstrate the superiority of our method against state-of-the-art baselines under distribution shifts. To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective.

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 37 code samples harvested from 5 repositories linked to this paper: 28 ran (of which 5 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 32 samples from 4 repositories, 24 ran (18 with no instrument failure; 6 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 4 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.

ringbdstack/eagle officialmentioned in paperpytorchSyntology: 5 samples, 4 ran (0 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.

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

37 samples harvested: 28 ran (of which 5 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 6 where Syntology's instrument failed) · 9 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.

5ran · our draft was wrong
1ran; the contract check could not run
22ran
9unverified

Licence: 25 of the 37 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 5 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 1 sample 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ringbdstack/eagle official repository 5 samples, 4 ran (0 instrument-failed) · 1 unverified
EAConv EAGLE/model.py ran · metamorphic tier: deterministic MIT (permissive) · 7b111062208ff6c2 · report fixture: returned EAConv · level recorded 2026-09-22
MultiplyPredictor EAGLE/model.py ran MIT (permissive) · 1dcc661e33d40239 · report fixture: signature z:Tensor/2/float, e:Tensor/2/int · returned Tensor · level recorded 2026-09-24
RelTemporalEncoding EAGLE/model.py ran · metamorphic tier: deterministic MIT (permissive) · 921c624bb8216cd2 · report fixture: returned RelTemporalEncoding · level recorded 2026-09-22
SparseInputLinear EAGLE/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 7b711f5caf31547a · report fixture: returned SparseInputLinear · level recorded 2026-09-22
EADGNN EAGLE/model.py unverified MIT (permissive) · 9875f37797e1a63a · report
facebookresearch/InvariantRiskMinimization found in paper text by Syntology 5 samples, 5 ran (1 instrument-failed) · 0 unverified
ls code/figure_1/penalties.py ran fingerprinted licence not identified · pointer only · 441553fde0ae7632 · report fixture: signature x:ndarray/2/float, y:ndarray/1/float, reg:float/0/float · returned ndarray · level recorded 2026-09-24
parse_title code/experiment_synthetic/plot.py ran licence not identified · pointer only · daef07c0b3b3c868 · report fixture: signature title:str/0/str · returned str · level recorded 2026-09-24
penalty_ls code/figure_1/penalties.py ran licence not identified · pointer only · cf65d91b550d6d66 · report fixture: signature x1:ndarray/2/float, y1:ndarray/1/float, x2:ndarray/2/float, y2:ndarray/1/float, t:float/0/float, reg:float/0/float · returned float64 · level recorded 2026-09-24
pretty in 10 papers code/experiment_synthetic/models.py ran · our draft was wrong no licence file found · pointer only · db4d05619d1e83d4 · report fixture: signature vector:Tensor/2/float · returned str · level recorded 2026-09-22
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
code/figure_1/penalties.py ran licence not identified · pointer only · 093b0b49240474d2 · report fixture: signature n:int/0/int, e:int/0/int · returned tuple · level recorded 2026-09-24
IBM/EvolveGCN found in paper text by Syntology 7 samples, 4 ran (1 instrument-failed) · 3 unverified
Namespace egcn_h.py ran Apache-2.0 (permissive) · c8545f3370c7f812 · report fixture: returned Namespace · level recorded 2026-09-22
TopK egcn_h.py ran Apache-2.0 (permissive) · 7f9c4e0d8cbff75f · report fixture: signature node_embs:Tensor/2/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-24
mat_GRU_gate egcn_h.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 769a39be26f32bb1 · report fixture: returned mat_GRU_gate · level recorded 2026-09-22
pad_with_last_val egcn_h.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b4a1a41169b57e33 · report fixture: signature vect:Tensor/1/int, k:int/0/int · returned Tensor · level recorded 2026-09-22
EGCN egcn_h.py unverified Apache-2.0 (permissive) · 5342821849fd3d94 · report
GRCU egcn_h.py unverified Apache-2.0 (permissive) · 12e1bb464511cd9c · report
mat_GRU_cell egcn_h.py unverified Apache-2.0 (permissive) · d499274fa52f6c1f · report
FeiGSSS/DySAT_pytorch found in paper text by Syntology 10 samples, 6 ran (1 instrument-failed) · 4 unverified
alias_draw in 6 papers utils/random_walk.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 9e04436adf3455c1 · report fixture: signature J:ndarray/1/int, q:ndarray/1/float · returned int64 · level recorded 2026-09-22
getDateTimeFromISO8601String raw_data/Enron/process.py ran no licence file found · pointer only · 10a9d52607534959 · report fixture: signature s:str/0/str · returned datetime · level recorded 2026-09-24
get_link_feats eval/link_prediction.py ran no licence file found · pointer only · c4ef46b2a2cc4c2a · report fixture: signature links:list/1/tuple, source_embeddings:list/1/ndarray, target_embeddings:list/1/ndarray, operator:str/0/str · returned list · level recorded 2026-09-24
get_link_score eval/link_prediction.py ran no licence file found · pointer only · 06bb274a882a8a1f · report fixture: signature fu:ndarray/1/float, fv:ndarray/1/float, operator:str/0/str · returned ndarray · level recorded 2026-09-24
get_random_split eval/link_prediction.py ran no licence file found · pointer only · 42cab9f471d1762d · report fixture: signature train_pos:list/1/int, train_neg:list/1/int, val_pos:list/1/int, val_neg:list/1/int, test_pos:list/1/int, test_neg:list/1/int · returned tuple · level recorded 2026-09-24
to_device in 75 papers utils/utilities.py ran no licence file found · pointer only · 366b610e7940bfb7 · report fixture: signature batch:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-24
alias_setup in 6 papers utils/random_walk.py unverified no licence file found · pointer only · 0f462717a557f615 · report
fixed_unigram_candidate_sampler utils/utilities.py unverified no licence file found · pointer only · 975bf2a81565b9c3 · report
get_evaluation_data utils/preprocess.py unverified no licence file found · pointer only · 1d593666381d1212 · report
load_graphs in 7 papers utils/preprocess.py unverified no licence file found · pointer only · c15dd381ad4028d7 · report
wondergo2017/DIDA found in paper text by Syntology 10 samples, 9 ran (3 instrument-failed) · 1 unverified
get_arg_dict DIDA/utils/mutils.py ran no licence file found · pointer only · 912f00fb9d64eebe · report fixture: signature args:MockArgs/0/? · returned dict · level recorded 2026-09-24
init_logger in 50 papers DIDA/utils/util.py ran no licence file found · pointer only · 3cd9fad3aabd89b3 · report fixture: signature log_file:str/0/str · returned RootLogger · level recorded 2026-09-24
is_empty_edges DIDA/utils/mutils.py ran no licence file found · pointer only · acb58bbdf2fd14a7 · report fixture: signature edges:Tensor/2/int · returned bool · level recorded 2026-09-24
map2id DIDA/utils/mutils.py ran fingerprinted no licence file found · pointer only · 557258293ecfd892 · report fixture: signature l:list/1/str · returned dict · level recorded 2026-09-24
mkdirs in 7 papers DIDA/utils/data_util.py ran · our draft was wrong no licence file found · pointer only · 520dfca725ed1118 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-24
mkdirs in 7 papers DIDA/utils/util.py ran no licence file found · pointer only · 01f2dcc14868226d · report fixture: signature folder:str/0/str · returned str · level recorded 2026-09-24
prepare_dir DIDA/utils/data_util.py ran · our draft was wrong no licence file found · pointer only · 060b44f5278742c2 · report fixture: signature output_folder:str/0/str · returned str · level recorded 2026-09-24
select_by_field DIDA/utils/data_util.py ran no licence file found · pointer only · 7187eb430177392f · report fixture: signature edges:Tensor/2/int, fields:list/1/int · returned list · level recorded 2026-09-24
xavier_init in 18 papers DIDA/utils/inits.py ran · our draft was wrong no licence file found · pointer only · 072c717f02e44012 · report fixture: signature shape:tuple/1/int · returned Tensor · level recorded 2026-09-24
mp_exec DIDA/utils/mp.py unverified no licence file found · pointer only · 8fca4741f029cd21 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for EAGLE (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for EAGLE (graph method: EAGLE). 5 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. EADGNN entry · level 0 · unverified · 9875f37797e1a63a
  2. EAConv model · level 1 · ran · 7b111062208ff6c2
  3. MultiplyPredictor helper · level 1 · ran · 1dcc661e33d40239
  4. SparseInputLinear helper · level 1 · ran · 7b711f5caf31547a
  5. RelTemporalEncoding model · level 1 · ran · 921c624bb8216cd2

harvested Assembly for EAGLE (graph method: EAGLE). 7 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. EGCN entry · level 0 · unverified · 5342821849fd3d94
  2. GRCU model · level 0 · unverified · 12e1bb464511cd9c
  3. Namespace helper · level 1 · ran · c8545f3370c7f812
  4. mat_GRU_cell model · level 0 · unverified · d499274fa52f6c1f
  5. TopK helper · level 1 · ran · 7f9c4e0d8cbff75f
  6. mat_GRU_gate model · level 1 · ran · 769a39be26f32bb1
  7. pad_with_last_val helper · level 1 · ran · our draft was wrong · b4a1a41169b57e33

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="2311.11114") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph LearningOut-of-Distribution Generalization

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