Papers › Temporal Graph Networks for Deep Learning on Dynamic Graphs

Temporal Graph Networks for Deep Learning on Dynamic Graphs

18 Jun 2020arXiv:2006.10637archive 2025-07-28

Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, Michael Bronstein

Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems. Despite the plethora of different models for deep learning on graphs, few approaches have been proposed thus far for dealing with graphs that present some sort of dynamic nature (e.g. evolving features or connectivity over time). In this paper, we present Temporal Graph Networks (TGNs), a generic, efficient framework for deep learning on dynamic graphs represented as sequences of timed events. Thanks to a novel combination of memory modules and graph-based operators, TGNs are able to significantly outperform previous approaches being at the same time more computationally efficient. We furthermore show that several previous models for learning on dynamic graphs can be cast as specific instances of our framework. We perform a detailed ablation study of different components of our framework and devise the best configuration that achieves state-of-the-art performance on several transductive and inductive prediction tasks for dynamic graphs.

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 19 code samples harvested from 5 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 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: community (archive-listed): 19 samples from 5 repositories, 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.

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.

KimMeen/TGN mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
M-Lampert/DyGLib mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Better Dynamic Graph Learning: New Architecture and Unified Library (arXiv:2303.13047; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Mohit-Mithra/ceiling-graph mentioned on GitHubpytorchSyntology: not harvested report
fpour/tgb_baselines mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Graph Benchmark for Machine Learning on Temporal Graphs (arXiv:2307.01026; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
jasperzhong/GNNFlow mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
petersh6/mspipe mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
twitter-research/tgn mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
wyd1502/DGNN mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
yule-buaa/dyglib mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph... (arXiv:2602.00596; that paper's own run record: 14 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
dmlc/dgl pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to node2vec: Scalable Feature Learning for Networks (arXiv:1607.00653; that paper's own run record: 15 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified), Interaction Networks for Learning about Objects, Relations and Physics (arXiv:1612.00222; that paper's own run record: 6 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; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result), Junction Tree Variational Autoencoder for Molecular Graph Generation (arXiv:1802.04364; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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

19 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 8 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.

3ran · our draft was wrong
1ran; the contract check could not run
7ran
8unverified

Licence: 0 of the 19 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”. “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.

KimMeen/TGN community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
utils/preprocess_data.py ran · our draft was wrong MIT (permissive) · 3e0dea4b496f8cd2 · report fixture: signature data_name:str/0/str · returned tuple · level recorded 2026-09-22
reindex in 5 papers utils/preprocess_data.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · 4b8167621054e800 · report fixture: signature df:DataFrame/0/?, bipartite:bool/0/bool · returned DataFrame · level recorded 2026-09-22
jasperzhong/GNNFlow community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
load_dataset in 276 papers gnnflow/utils.py ran Apache-2.0 (permissive) · 59bf623a3b88b301 · report fixture: signature dataset:str/0/str, data_dir:str/0/str · returned tuple · level recorded 2026-09-24
get_default_config in 6 papers gnnflow/config.py unverified Apache-2.0 (permissive) · 2abeac7066079ca7 · report
load_partition_table gnnflow/utils.py unverified Apache-2.0 (permissive) · 7de6a93ec6c03c40 · report
load_partition_table gnnflow/utils.py unverified Apache-2.0 (permissive) · 01f22d83afe320b6 · report
petersh6/mspipe community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
neg_sample in 9 papers tgl/offline_tgl_presample.py ran Apache-2.0 (permissive) · 5434bcfd6e9908b3 · report fixture: signature target_nodes:ndarray/1/int, ts:ndarray/1/float, nodes:ndarray/1/int · returned tuple · level recorded 2026-09-24
get_default_config in 6 papers gnnflow/config.py unverified Apache-2.0 (permissive) · 61d785f64b05116b · report
twitter-research/tgn community (archive-listed) 8 samples, 5 ran (0 instrument-failed) · 3 unverified
compute_time_statistics utils/data_processing.py ran Apache-2.0 (permissive) · 6a8c69478a373575 · report fixture: signature sources:ndarray/1/int, destinations:ndarray/1/int, timestamps:ndarray/1/float · returned tuple · level recorded 2026-09-24
eval_edge_prediction evaluation/evaluation.py ran Apache-2.0 (permissive) · f5baa0e9f4ee3f74 · report fixture: signature model:callable/0/?, negative_edge_sampler:MockNegativeEdgeSampler/0/?, data:MockData/0/?, n_neighbors:int/0/int, batch_size:int/0/int · returned tuple · level recorded 2026-09-24
get_memory_updater modules/memory_updater.py ran Apache-2.0 (permissive) · 5ac1084a72c973aa · report fixture: signature module_type:str/0/str, memory:callable/0/?, message_dimension:int/0/int, memory_dimension:int/0/int, device:str/0/str · returned GRUMemoryUpdater · level recorded 2026-09-24
get_message_aggregator modules/message_aggregator.py ran Apache-2.0 (permissive) · 74cf96ac89330114 · report fixture: signature aggregator_type:str/0/str, device:str/0/str · returned LastMessageAggregator · level recorded 2026-09-24
get_message_function modules/message_function.py ran Apache-2.0 (permissive) · e6724c779cc863ee · report fixture: signature module_type:str/0/str, raw_message_dimension:int/0/int, message_dimension:int/0/int · returned MLPMessageFunction · level recorded 2026-09-24
eval_node_classification evaluation/evaluation.py unverified Apache-2.0 (permissive) · ce54929f6e81f2e2 · report
get_data in 223 papers utils/data_processing.py unverified Apache-2.0 (permissive) · d0e882ad0635a4cb · report
get_data_node_classification utils/data_processing.py unverified Apache-2.0 (permissive) · 1b8c08588991e985 · report
wyd1502/DGNN community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
choose_target evaluation.py ran · our draft was wrong MIT (permissive) · 0cefebdbffe30631 · report fixture: signature model:callable/0/?, memory_s:list/1/Tensor, memory_g:list/1/Tensor, src_mem:Tensor/2/float · returned tuple · level recorded 2026-09-22
recall in 38 papers evaluation.py ran · our draft was wrong fingerprinted MIT (permissive) · 4d2b9553dedc1537 · report fixture: signature des_node:ndarray/1/int, idx:ndarray/2/int, top_k:int/0/int · returned float64 · level recorded 2026-09-22
MRR evaluation.py unverified MIT (permissive) · 3537ea56146f8de9 · report

Tasks

Deep LearningRecommendation Systems

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: TGN

TGN

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