SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.15865 · NeurIPS · 2024

Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs

Franziska Heeg, Ingo Scholtes

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2310.15865.json · badge: /api/ran/2310.15865.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
pathpy/pathpyg canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
aggregate_node_attributes Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pathpy/pathpyg/src/pathpyG/algorithms/lift_order.py
pointer only (licence: AGPL-3.0) · get_code("d0c055f0457b0c15")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, pathpy/pathpyg, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

lift_order_edge_index Ran
ran; our contract draft was wrong, not the code
pathpy/pathpyg/src/pathpyG/algorithms/lift_order.py
pointer only (licence: AGPL-3.0) · get_code("5573040885a5d8d0")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, pathpy/pathpyg, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

lift_order_edge_index_weighted Ran
ran; our contract draft was wrong, not the code
pathpy/pathpyg/src/pathpyG/algorithms/lift_order.py
pointer only (licence: AGPL-3.0) · get_code("4456b5c765ff2a97")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, pathpy/pathpyg, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

max_edges Ran
ran, honoured the contract we drafted
pathpy/pathpyg/src/pathpyG/algorithms/generative_models.py
pointer only (licence: AGPL-3.0) · get_code("860743ab3e1227ce")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, pathpy/pathpyg, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Node centralities play a pivotal role in network science, social network analysis, and recommender systems. In temporal data, static path-based centralities like closeness or betweenness can give misleading results about the true importance of nodes in a temporal graph. To address this issue, temporal generalizations of betweenness and closeness have been defined that are based on the shortest time-respecting paths between pairs of nodes. However, a major issue of those generalizations is that the calculation of such paths is computationally expensive. Addressing this issue, we study the application of De Bruijn Graph Neural Networks (DBGNN), a time-aware graph neural network architecture, to predict temporal path-based centralities in time series data. We experimentally evaluate our approach in 13 temporal graphs from biological and social systems and show that it considerably improves the prediction of betweenness and closeness centrality compared to (i) a static Graph Convolutional Neural Network, (ii) an efficient sampling-based approximation technique for temporal betweenness, and (iii) two state-of-the-art time-aware graph learning techniques for dynamic graphs. Node centralities are important in the analysis of complex networks, with applications in network science, social network analysis, and recommender systems. An important class of centrality measures are path-based centralities like, e.g. betweenness or closeness centrality [5,16], which are based on the shortest paths between all nodes. While centralities in static networks are important, we increasingly have access to time series data on temporal graphs with time-stamped edges. Due to the timing and ordering of those edges, the paths in a static time-aggregated representation of such time series data can considerably differ from time-respecting paths in the corresponding temporal graph. In a nutshell, two time-stamped edges (u, v; t) and (v, w; t ′ ) only form a time-respecting path from node u via v to w iff for the time stamps t and t ′ we have t < t ′ , i.e. time-respecting paths must minimally respect the arrow of time. Moreover, we often consider scenarios where we need to additionally account for a maximum time difference δ between time-stamped edges, i.e. we require 0 < t ′ -t ≤ δ [22]. Several works have shown that temporal correlations in the sequence of time-stamped edges can significantly change the causal topology of a temporal graph, i.e. which nodes can influence each other via time-respecting paths, compared to what is expected based on the static topology [30,35,39]. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.15865")
get_code_for_paper("2310.15865")
have("2310.15865")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2310.15865.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2310.15865.svg)](https://syntology.ai/paper/2310.15865)

Connect an agent — have() is free.