Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features

Emiliano Pallotti; Federica Mangiatordi; Giambattista Amati; Paola Vocca; Pierpaolo Salvo; Simone Angelini

REVIEW

Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features

Giambattista Amati, Federica Mangiatordi, Emiliano Pallotti, Simone Angelini, Pierpaolo Salvo, Paola Vocca

Machine Learning · Submitted 15 Jul 2026 · 24 references

Pith's verdict: A solid, honest L2O engineering paper with a real task and a real feasibility gap: the learned edge activations are never checked against the MILP's routing constraints, so the connectivity-gain numbers are probably optimistic but the core link-level result is measured and worth reviewing.

T0 · AI review

How this review was made: An AI referee (deepseek-v4-flash) read the paper on August 2, 2026 and answered a fixed list of questions about it. T0 is the starting level every paper gets. The levels describe how deeply Pith has checked the paper, never the authors.

T0 AI review An AI read the paper and answered a fixed list of questions.
T1 Audit Automatic checks that the references and files the paper relies on exist and match.
T2 Compute The paper's code or calculations re-run with the same results.
T3 Formal statement The claims written out in a formal math language a computer can read.
T4 Proof Those claims proved, and the proof checked by computer.

How Pith checks papers →

· 3 major objections · 5 minor · Ask about this paper · The compiled record · Read the full review →

Challenge this review Comment (0) Read on arXiv ↗

Cite ▾

arXiv ID2607.14176 (version 1)

Pith IDTPSJG6W3, Pith's permanent record of this paper and its review

CitationEmiliano Pallotti, Federica Mangiatordi, Giambattista Amati, Paola Vocca, Pierpaolo Salvo, Simone Angelini. "Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features." arXiv:2607.14176 (2026). https://pith.science/paper/TPSJG6W3

Cite this reviewBibTeX for Pith's review of this paper

Claim paper

Why Pith says this

Highlight any text to comment on it.

Editor's note

read the letter

You should know three things about this one: it is a genuine learning-to-optimize application to multi-hop relay selection in NR-V2X, the paper is honest about its own main limitation, and the central evaluation metric has a hole that the authors acknowledge but do not fix.

What is actually new: framing relay selection as edge-level GINE classification supervised by a MILP oracle, plus the GP-MILP pruning hybrid. The architecture itself is standard GINE + BCE loss, but the task framing is new in the cited literature, and the GP-MILP result — 98% of instances under 30 ms with the same objective value as full MILP — is a concrete, practical claim. The dataset is large (449,500 snapshots) and built from a realistic OSM-SUMO-GEMV2 pipeline. Link-level accuracy 0.9589 / F1 0.9544 is directly measured and, absent code, at least clearly specified.

The soft spots, in order of real softness. First and most important: the paper explicitly says the GINE does not enforce routing or flow-conservation constraints at inference. The end-to-end connectivity metric then counts a vehicle as connected if it can reach an RSU over any activated edge set, including sets with cycles or multiple outgoing links. That means the reported 9.2% and 12% connectivity gains over the 1-hop MILP baseline may be inflated by infeasible configurations. This is a load-bearing weakness, not a cosmetic one, and the stress-test note is right to flag it. The authors do disclose it up front and list constraint-aware post-processing as future work, so the paper is not hiding anything, but the headline gains should be treated as optimistic until feasibility is checked or enforced. Second: no error bars or confidence intervals on any metric, and no code or data release, which makes the 96% agreement hard to verify independently. Third: GP-MILP's "MILP-equivalent" claim is empirical on the evaluated dataset; there is no proof that pruning preserves optimality, and the threshold choice (0.15) is sensible but not analyzed. Fourth: the only baseline is the 1-hop MILP; no comparison to other learned or heuristic relay-selection methods.

All that said, the link-level agreement is a real measurement, the paper is clearly written, and the limitations are stated rather than buried. This is not circular: the GINE is trained on MILP labels and evaluated on agreement with those labels, which is standard L2O practice, not a logical circle. I would send this to a serious referee. It deserves review and probably a major revision that addresses the feasibility gap and adds uncertainty quantification. The core idea is solid enough to build on.

For your reading group, worth a maybe; for my own citation, not this year.

Referee report

Significance

If the results hold, the work demonstrates a practical route to real-time relay selection with near-optimal quality, which would be valuable for low-latency NR-V2X. Strengths include the use of a large realistic simulation pipeline, the explicit adoption of an edge-aware GINE architecture, the hybrid pruning idea, and an honest disclosure of the model's limitations in the text. The main weakness is that the GINE output is not validated as a feasible relay configuration: the connectivity metric counts reachability through activated edges without enforcing the actual routing constraints of the problem. This gap is acknowledged in Section I and deferred to future work, but it is load-bearing for the central claim of 'relay selection' quality. The paper should therefore be revised to either enforce constraints at inference, report feasibility rates, or reframe the claims.

Major objections (3)

[Section VI-C; Eq. (2), (4), (5)] The end-to-end connectivity metric counts a vehicle as connected if it can reach an RSU over activated directed edges, but it does not require that the activated edge set satisfy the MILP's single-outgoing-link, flow-conservation, or loop-free constraints. A configuration with two outgoing links from one CAV or a cycle is treated as connected even though no valid single-path uplink route exists. The paper explicitly concedes in Section I that routing/flow constraints are not enforced at inference, and Section VII lists 'constraint-aware post-processing' as future work. No feasibility rate of GINE outputs is reported. Consequently, the reported 9.2% and 12% connectivity gains over the 1-hop MILP baseline may be inflated by infeasible edge sets. Please report the fraction of GINE outputs that satisfy Eqs. (2), (4), (5), and recompute connectivity on a feasible projection or after post-proc
[Section VI-A / Section IV] The MILP oracle is described as providing 'optimal' relay configurations, but the experimental setup imposes a per-instance time limit of 11 s. If any instances reach this limit, the ground-truth labels are not necessarily optimal, and the GINE's 'close agreement' is relative to potentially suboptimal labels. Similarly, the GP-MILP claim of 'preserving MILP-equivalent solutions (same objective value)' is only meaningful if the base MILP solves are proven optimal. Please report the percentage of instances solved to proven optimality within the time limit, the distribution of relative MILP gaps (e.g., objective bound gap) for time-limited instances, and whether GP-MILP changes those gaps.
[Table I / Section VI-B] All link-level metrics (accuracy, precision, recall, F1) are reported as point estimates on a single validation split, with no confidence intervals or multiple-seed training runs. The threshold sweep is performed on the same validation set, which can overestimate performance if thresholds are selected on the evaluation set. In addition, the connectivity gains in Section VI-C (9.2%, 12%) are reported without variance estimates or significance tests. Please add error bars (e.g., 95% CI over multiple seeds or bootstrapping), and ideally report results on a held-out test set that is not used for threshold selection.

Minor objections (5)

[Section VI-A] Typo: 'iactive' should be 'inactive'. Throughout, the spacing around 'CA V' is inconsistent (e.g., 'CA Vs' vs. 'CAVs').
[Section VI-D] Typo: 'stategy' should be 'strategy' in the sentence '...optimisation stategy effectively compatible...'.
[Table II and Figure 2] The table reports only percentages meeting latency thresholds; please also report mean/median and standard deviation of inference and solver runtimes, since the claim 'within 5 ms' is based on the mean over 10 runs per instance, which may mask tail latency. Figure 2 clips runtimes above 9 s; consider showing the full distribution or a log-scale inset.
[Section V-D] The class weight α is computed from training statistics; please specify exactly when this is computed (prior to training) and report the value, since it directly affects the loss in Eq. (9).
[References] Reference [23] is duplicated as [22] and [23] in the bibliography (both point to the GEMV2 model). Also, please check if the dataset and simulation code will be released, as the paper currently provides no link to code or data.

How Pith checks papers → · Full audit of this paper →

The paper

The paper claims

This paper claims that a graph isomorphism network trained on exact mixed-integer solutions can select multi-hop V2X relay links with about 95% link-level F1 and all inference runs under 5 ms, bringing optimal-grade relay selection into rea

The reading

The paper tries to show that relay selection in NR-V2X vehicular networks, normally an NP-hard optimization solved by mixed-integer linear programming (MILP) with runtimes that scale poorly with graph size, can be delegated to a graph neural network trained on MILP-generated examples. The model, a Graph Isomorphism Network with Edge Features (GINE), classifies each directed link as active or inactive in a single forward pass. The paper reports close agreement with MILP decisions at the link level (F1 around 0.954) and consistent connectivity gains over a one-hop baseline (9-12%). It also shows that a hybrid GP-MILP scheme, where the network prunes the MILP search space, preserves the same objective value while keeping 98% of solver runs under 30 ms. A sympathetic reader should take away that learned surrogate optimization can plausibly fit within NR-V2X latency budgets, provided the model outputs are treated as feasible relay configurations.

What carries the argument

The central object is the GINE encoder with edge features: each directed link's radio capacity is projected through an MLP and injected into the message-passing updates, so the model sees not only topology but link quality. A classification head concatenates source and destination node embeddings with the edge feature and outputs an activation probability for each edge. Training uses MILP-optimal binary activation matrices as ground truth with class-weighted binary cross-entropy loss. For the hybrid GP-MILP, the same network's low-threshold predictions prune edges from the graph before MILP solving, shrinking the search space while retaining oracle-active links with high recall.

Extended reading notes

Core claim

The central claim is that an edge-aware GINE, supervised offline by a MILP oracle that maximizes the number of vehicles with a valid loop-free uplink path, learns to reproduce optimal relay activations at the edge level: accuracy 0.9589 and F1 0.9544 on validation. The learned model yields end-to-end connectivity gains of 9.2% with four RSUs and 12% with two RSUs over a 1-hop MILP baseline, with all tested instances completing inference in under 5 ms. The companion GP-MILP hybrid, which uses GINE predictions to prune the graph given to the MILP solver, attains the same objective values as the full MILP while completing 98.14% of instances in under 30 ms. As the paper states in Section I, the

Load-bearing premise

The load-bearing premise is that the neural model's unconstrained edge activations can be treated as feasible relay configurations, since the paper counts a vehicle as connected if it reaches an RSU over activated edges without checking the MILP's single-outgoing-link, flow-conservation, and loop-free constraints.

Editorial extensions

If this is right

If GINE accurately approximates MILP decisions, relay selection can shift from an online solver to a trained forward pass, removing exponential worst-case solve times from the decision loop.
The GP-MILP result implies that MILP-equivalent optimization can run within 30 ms for the vast majority of dense urban snapshots, meeting tighter latency budgets than unpruned MILP.
The 9-12% connectivity gains over a 1-hop baseline quantify the real-world value of coordinated multi-hop relaying in infrastructure-sparse urban deployments.
Because inference complexity scales linearly with the number of edges for a fixed network depth, the approach offers predictable latency as graph size grows.

Reading between the lines

Editorial extensions of the paper, not claims the author makes directly.

If GINE outputs were passed through a lightweight feasibility repair that enforces single-outgoing-link and loop-free constraints, the reported accuracy numbers would translate more directly into deployable relay schedules; the paper's future-work note on constraint-aware post-processing points in this direction.
The threshold sweep suggests a family of operating points: a system designer could choose recall-oriented thresholds when preserving connectivity matters more than minimizing relay count, or precision-oriented thresholds to limit interference.
A natural extension is temporal: feeding consecutive GINE outputs could detect unstable relay flips, and the paper's future-work mention of temporal graph sequences signals that the authors intend this direction.
The pruning result hints that learned models can serve not only as replacements for optimization but as accelerators of exact solvers, a pattern transferable to other NP-hard network optimizations with expensive feasibility constraints.

Original abstract

Reliable, low-latency uplink connectivity is a key requirement for C-V2X networks in dense urban environments, where fast channel variations and blockages often degrade direct vehicle-to-infrastructure links. Multi-hop relaying can restore coverage, but relay-link activation under radio, capacity, and routing constraints results in an NP-hard optimisation problem, typically solved via Mixed-Integer Linear Programming (MILP), whose runtime scales poorly with graph size. This paper introduces an edge-aware Learning-to-Optimise framework for real-time relay selection. Each V2X snapshot is modelled as a directed graph: node features encode vehicle state and traffic demand, while edge features capture radio-link capacity. An offline MILP oracle generates optimal relay configurations that supervise a Graph Isomorphism Network with Edge Features (GINE), enabling edge-level relay activation through a single forward pass, with tightly bounded inference latency. To bridge learning and exact optimisation, we also propose a hybrid GINE-Pruned MILP (GP-MILP) strategy in which GINE predictions prune the MILP search space. Experiments on a large-scale dataset generated via an OSM-SUMO-GEMV$^2$ pipeline show that GINE closely matches MILP decisions at the link level (accuracy 0.9589), F1-score (0.9544) on validation) and yields consistent end-to-end connectivity gains over a 1-hop MILP baseline (up to 9.2% with four RSUs and 12% with two RSUs). Inference latency remains tightly bounded, with all evaluated instances completing within 5~ms. Moreover, GP-MILP preserves MILP-equivalent solutions (same objective value) while achieving solver runtimes below 30~ms for more than 98%) of the graph instances, making MILP-grade optimisation compatible with stringent NR-V2X latency budgets.

The compiled record

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 7,287 input tokens.

What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.24 · human participants 0.02 · controlled comparison 0.95 · randomized assignment 0.01 · states quantitative result 0.99 · compares with prior results 0.97 · mentions code or data availability 0.03.

The abstract, sentence by sentence

arXiv listing abstract v1. Results and the main claim are underlined; show every role.

Reliable, low-latency uplink connectivity is a key requirement for C-V2X networks in dense urban environments, where fast channel variations and blockages often degrade direct vehicle-to-infrastructure links. Multi-hop relaying can restore coverage, but relay-link activation under radio, capacity, and routing constraints results in an NP-hard optimisation problem, typically solved via Mixed-Integer Linear Programming (MILP), whose runtime scales poorly with graph size. This paper introduces an edge-aware Learning-to-Optimise framework for real-time relay selection. Each V2X snapshot is modelled as a directed graph: node features encode vehicle state and traffic demand, while edge features capture radio-link capacity. An offline MILP oracle generates optimal relay configurations that supervise a Graph Isomorphism Network with Edge Features (GINE), enabling edge-level relay activation through a single forward pass, with tightly bounded inference latency. To bridge learning and exact optimisation, we also propose a hybrid GINE-Pruned MILP (GP-MILP) strategy in which GINE predictions prune the MILP search space. Experiments on a large-scale dataset generated via an OSM-SUMO-GEMV$^2$ pipeline show that GINE closely matches MILP decisions at the link level (accuracy 0.9589), F1-score (0.9544) on validation) and yields consistent end-to-end connectivity gains over a 1-hop MILP baseline (up to 9.2% with four RSUs and 12% with two RSUs). Inference latency remains tightly bounded, with all evaluated instances completing within 5~ms. Moreover, GP-MILP preserves MILP-equivalent solutions (same objective value) while achieving solver runtimes below 30~ms for more than 98%) of the graph instances, making MILP-grade optimisation compatible with stringent NR-V2X latency budgets.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	Reliable, low-latency uplink connectivity is a key requirement for C-V2X networks in dense urban environments, where fast channel variations and blockages often degrade direct vehicle-to-infrastructure links.	background 1.00	0.06	0.02	asserted 1.00
s1	Multi-hop relaying can restore coverage, but relay-link activation under radio, capacity, and routing constraints results in an NP-hard optimisation problem, typically solved via Mixed-Integer Linear Programming (MILP), whose runtime scales poorly with graph size.	background 0.89	0.07	0.02	asserted 1.00
s2	This paper introduces an edge-aware Learning-to-Optimise framework for real-time relay selection.	contribution 0.99	0.88	0.11	asserted 0.99
s3	Each V2X snapshot is modelled as a directed graph: node features encode vehicle state and traffic demand, while edge features capture radio-link capacity.	method 1.00	0.79	0.02	asserted 1.00
s4	An offline MILP oracle generates optimal relay configurations that supervise a Graph Isomorphism Network with Edge Features (GINE), enabling edge-level relay activation through a single forward pass, with tightly bounded inference latency.	method 0.96	0.93	0.17	asserted 1.00
s5	To bridge learning and exact optimisation, we also propose a hybrid GINE-Pruned MILP (GP-MILP) strategy in which GINE predictions prune the MILP search space.	contribution 0.68	0.93	0.06	asserted 1.00
s6	Experiments on a large-scale dataset generated via an OSM-SUMO-GEMV$^2$ pipeline show that GINE closely matches MILP decisions at the link level (accuracy 0.9589), F1-score (0.9544) on validation) and yields consistent end-to-end connectivity gains over a 1-hop MILP baseline (up to 9.2% with four RSUs and 12% with two RSUs).	result 1.00	0.97	0.38	asserted 1.00
s7	Inference latency remains tightly bounded, with all evaluated instances completing within 5~ms.	result 1.00	0.95	0.10	asserted 1.00
s8	Moreover, GP-MILP preserves MILP-equivalent solutions (same objective value) while achieving solver runtimes below 30~ms for more than 98%) of the graph instances, making MILP-grade optimisation compatible with stringent NR-V2X latency budgets.	result 0.99	0.96	0.31	asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from simulation or computation 0.81.

What was examined, and what was not

sources read

arXiv listing abstract v1

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

Figures

**Figure 1.** GINE-based learning-to-optimise framework for multi-hop relay selection in NR-V2X networks.

**Figure 2.** Runtime as a function of the number of edges for the

Figures reproduced from arXiv:2607.14176 by the authors.

References

Works cited (24)

[1]

ETSI, “5G; Service Requirements for Enhanced V2X Scenarios,” European Telecommunications Standards Institute, Technical Specification ETSI TS 122 186 V18.0.1, 2024, release 18, May 2024

View on Pith 2024
[2]

3GPP, “Study on Enhanced Application Architecture for Enabling Edge Applications,” 3rd Generation Partnership Project, Technical Report TR 23.700-98, 2023, release 18

View on Pith 2023
[3]

S. Hakak, T. R. Gadekallu, P. K. R. Maddikunta, S. P. Ramu, P. M, C. De Alwis, and M. Liyanage, “Autonomous vehicles in 5g and beyond: A survey,”Vehicular Communications, vol. 39, p. 100551, 2023

View on Pith 2023
[4]

I. Soto, M. Calderon, O. Amador, and M. Urue ˜na, “A survey on road safety and traffic efficiency vehicular applications based on c-v2x technologies,”Veh. Commun., vol. 33, no. C, Jan. 2022. [Online]. Available: https://doi.org/10.1016/j.vehcom.2021.100428

View on Pith arXiv 2022
[5]

F. Jameel, S. Wyne, S. J. Nawaz, and Z. Chang, “Propagation channels for mmwave vehicular communications: State-of-the-art and future research directions,”IEEE Wireless Commun., vol. 26, pp. 144–150, 2018

View on Pith 2018
[6]

L. Taiya, M. Kai, Z. Qiuming, M. Zhangfeng, H. Boyu, W. Qihui et al., “Ultra-wideband channel modelling and characterisation under low altitude scenarios,”Chinese Journal of Aeronautics, p. 104077, 2026

View on Pith 2026
[7]

J. Clancy, D. Mullins, B. Deegan, J. Horgan, E. Ward, C. Eising, P. Denny, E. Jones, and M. Glavin, “Wireless access for v2x communications: Research, challenges and opportunities,”IEEE Commun. Surv. Tutor., vol. 26, no. 3, pp. 2082–2119, 2024

View on Pith
[8]

Q. Fu and J. Liu, “Generalized multi-hop nr sidelink relay for future v2x communication,”IEEE/ACM Transactions on Networking, vol. 32, no. 2, pp. 1691–1706, 2024

View on Pith 2024
[9]

Y . Chen, R. Zhang, and H. V . Poor, “Scalable optimization for large-scale networked systems: Limitations of mixed-integer programming,”IEEE Communications Surveys & Tutorials, 2024

View on Pith 2024
[10]

Z. Shao, J. Yang, C. Shen, and S. Ren, “Learning for robust combinatorial optimization: Algorithm and application,” 2021. [Online]. Available: https://arxiv.org/abs/2112.10377

View on Pith Pith review arXiv 2021
[11]

Y . Bengio, A. Lodi, and A. Prouvost, “Machine learning for combinatorial optimization: a methodological tour d’horizon,”European Journal of Operational Research, vol. 290, no. 2, pp. 405–421, 2021

View on Pith 2021
[12]

G. Amati, F. Mangiatordi, E. Pallotti, S. Angelini, and P. Salvo, “Topology intelligence: Gnn-powered 5g v2x,” in2025 AEIT International Annual Conference (AEIT), 2025, pp. 1–6

View on Pith 2025
[13]

X. Li, M. Chen, Y . Liu, Z. Zhang, D. Liu, and S. Mao, “Graph neural networks for joint communication and sensing optimisation in vehicular networks,”IEEE Journal on Selected Areas in Communications, vol. 41, no. 12, pp. 3893–3907, 2023

View on Pith 2023
[14]

G. Amati, F. Mangiatordi, E. Pallotti, S. Angelini, and P. Salvo, “5g-v2x topology intelligence: A gnn approach,” in2025 17th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), 2025, pp. 7–12

View on Pith 2025
[15]

T. Zhou, X. Wu, and X. Zhang, “Digital twin empowered mmwave multi-hop v2x routing scheme with uav assistance,”IEEE Transactions on Mobile Computing, vol. 24, no. 9, pp. 8272–8286, 2025

View on Pith 2025
[16]

L. Chen, J. Zhu, and J. Evans, “Gnn-based joint channel and power allocation in heterogeneous wireless networks,” in2024 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, 2024, pp. 233–238

View on Pith 2024
[17]

X. Jiang, R. Zhu, P. Ji, and S. Li, “Co-embedding of nodes and edges with graph neural networks,” 2020. [Online]. Available: https://arxiv.org/abs/2010.13242

View on Pith Pith review arXiv 2020
[18]

G. Amati, S. Angelini, F. Mangiatordi, E. Pallotti, and P. Salvo, “A massive clustering algorithm for fast radio resource allocation to distributed units in o-ran networks,” in2024 AEIT International Annual Conference (AEIT), 2024, pp. 1–6

View on Pith 2024
[19]

Y . Gu, C. She, Z. Quan, C. Qiu, and X. Xu, “Graph neural networks for distributed power allocation in wireless networks: Aggregation over-the-air,”IEEE Transactions on Wireless Communications, vol. 22, no. 11, pp. 7551–7564, 2023

View on Pith 2023
[20]

OpenStreetMap contributors. (2024) OpenStreetMap. [Online]. Available: https://www.openstreetmap.org

View on Pith 2024
[21]

P. Alvarez Lopez, A. Banse, M. Barthauer, M. Behrisch, B. Cou ´eraud, J. Erdmann, Y .-P. Fl ¨otter¨od, R. Hilbrich, R. Nippold, and P. Wagner, “Simulation of urban mobility (sumo),” Oct. 2024. [Online]. Available: https://doi.org/10.5281/zenodo.13907886

View on Pith doi:10.5281/zenodo.13907886 2024
[22]

M. Boban. GEMV 2 – geometry-based efficient propagation model for V2V communication. [Online]. Available: http://vehicle2x.net

View on Pith
[23]

Mate Boban, “Geometry-based Efficient propagation Model for V2V communication,” ”https://artery.v2x-research.eu/features/gemv2/”, 2020

View on Pith 2020
[24]

K. Ghosh, C. Bellinger, R. Corizzo, P. Branco, B. Krawczyk, and N. Japkowicz, “The class imbalance problem in deep learning,”Machine Learning, vol. 113, no. 7, pp. 4845–4901, 2024

View on Pith 2024

How the literature uses it

What this paper does with the arXiv papers it cites

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers whose main result relates to this one's

Found among the papers closest to this one by title and main claim. Pith's classifier compared each pair's main results and a second model family confirmed the relation; checked against two further families, shown conflicts agreed 118 times in 120 and shown same results 218 times in 239. The quoted sentence is the other paper's main claim.

States the same result 1 paper

Experiments on large-scale urban datasets generated by an integrated SUMO--GEMV2 simulation pipeline show that the proposed approach achieves connectivity comparable to that of the MILP oracle while reducing execution time by orders of magnitude.

AI-Driven Multi-Hop Relay Selection for Smart Urban NR-V2X Networks via Learning-to-Optimize Graph Neural Networks · 0.86

What it cites · 1 sentence without a confident label

Cites as background 1 paper

More recent studies have explored edge-centric graph representations, where relay or link activation decisions are formulated as edge classification problems or are addressed through line-graph constructions [ref] .

Co-embedding of Nodes and Edges with Graph Neural Networks · Related Work · 0.81

Discussion

Disagree with the review, or know something it missed? Leave a comment, highlight any passage above to comment on it, or challenge this review formally.

[1] [1]

ETSI, “5G; Service Requirements for Enhanced V2X Scenarios,” European Telecommunications Standards Institute, Technical Specification ETSI TS 122 186 V18.0.1, 2024, release 18, May 2024

View on Pith 2024

[2] [2]

3GPP, “Study on Enhanced Application Architecture for Enabling Edge Applications,” 3rd Generation Partnership Project, Technical Report TR 23.700-98, 2023, release 18

View on Pith 2023

[3] [3]

S. Hakak, T. R. Gadekallu, P. K. R. Maddikunta, S. P. Ramu, P. M, C. De Alwis, and M. Liyanage, “Autonomous vehicles in 5g and beyond: A survey,”Vehicular Communications, vol. 39, p. 100551, 2023

View on Pith 2023

[4] [4]

I. Soto, M. Calderon, O. Amador, and M. Urue ˜na, “A survey on road safety and traffic efficiency vehicular applications based on c-v2x technologies,”Veh. Commun., vol. 33, no. C, Jan. 2022. [Online]. Available: https://doi.org/10.1016/j.vehcom.2021.100428

View on Pith arXiv 2022

[5] [5]

F. Jameel, S. Wyne, S. J. Nawaz, and Z. Chang, “Propagation channels for mmwave vehicular communications: State-of-the-art and future research directions,”IEEE Wireless Commun., vol. 26, pp. 144–150, 2018

View on Pith 2018

[6] [6]

L. Taiya, M. Kai, Z. Qiuming, M. Zhangfeng, H. Boyu, W. Qihui et al., “Ultra-wideband channel modelling and characterisation under low altitude scenarios,”Chinese Journal of Aeronautics, p. 104077, 2026

View on Pith 2026

[7] [7]

J. Clancy, D. Mullins, B. Deegan, J. Horgan, E. Ward, C. Eising, P. Denny, E. Jones, and M. Glavin, “Wireless access for v2x communications: Research, challenges and opportunities,”IEEE Commun. Surv. Tutor., vol. 26, no. 3, pp. 2082–2119, 2024

View on Pith

[8] [8]

Q. Fu and J. Liu, “Generalized multi-hop nr sidelink relay for future v2x communication,”IEEE/ACM Transactions on Networking, vol. 32, no. 2, pp. 1691–1706, 2024

View on Pith 2024

[9] [9]

Y . Chen, R. Zhang, and H. V . Poor, “Scalable optimization for large-scale networked systems: Limitations of mixed-integer programming,”IEEE Communications Surveys & Tutorials, 2024

View on Pith 2024

[10] [10]

Z. Shao, J. Yang, C. Shen, and S. Ren, “Learning for robust combinatorial optimization: Algorithm and application,” 2021. [Online]. Available: https://arxiv.org/abs/2112.10377

View on Pith Pith review arXiv 2021

[11] [11]

Y . Bengio, A. Lodi, and A. Prouvost, “Machine learning for combinatorial optimization: a methodological tour d’horizon,”European Journal of Operational Research, vol. 290, no. 2, pp. 405–421, 2021

View on Pith 2021

[12] [12]

G. Amati, F. Mangiatordi, E. Pallotti, S. Angelini, and P. Salvo, “Topology intelligence: Gnn-powered 5g v2x,” in2025 AEIT International Annual Conference (AEIT), 2025, pp. 1–6

View on Pith 2025

[13] [13]

X. Li, M. Chen, Y . Liu, Z. Zhang, D. Liu, and S. Mao, “Graph neural networks for joint communication and sensing optimisation in vehicular networks,”IEEE Journal on Selected Areas in Communications, vol. 41, no. 12, pp. 3893–3907, 2023

View on Pith 2023

[14] [14]

G. Amati, F. Mangiatordi, E. Pallotti, S. Angelini, and P. Salvo, “5g-v2x topology intelligence: A gnn approach,” in2025 17th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), 2025, pp. 7–12

View on Pith 2025

[15] [15]

T. Zhou, X. Wu, and X. Zhang, “Digital twin empowered mmwave multi-hop v2x routing scheme with uav assistance,”IEEE Transactions on Mobile Computing, vol. 24, no. 9, pp. 8272–8286, 2025

View on Pith 2025

[16] [16]

L. Chen, J. Zhu, and J. Evans, “Gnn-based joint channel and power allocation in heterogeneous wireless networks,” in2024 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, 2024, pp. 233–238

View on Pith 2024

[17] [17]

X. Jiang, R. Zhu, P. Ji, and S. Li, “Co-embedding of nodes and edges with graph neural networks,” 2020. [Online]. Available: https://arxiv.org/abs/2010.13242

View on Pith Pith review arXiv 2020

[18] [18]

G. Amati, S. Angelini, F. Mangiatordi, E. Pallotti, and P. Salvo, “A massive clustering algorithm for fast radio resource allocation to distributed units in o-ran networks,” in2024 AEIT International Annual Conference (AEIT), 2024, pp. 1–6

View on Pith 2024

[19] [19]

Y . Gu, C. She, Z. Quan, C. Qiu, and X. Xu, “Graph neural networks for distributed power allocation in wireless networks: Aggregation over-the-air,”IEEE Transactions on Wireless Communications, vol. 22, no. 11, pp. 7551–7564, 2023

View on Pith 2023

[20] [20]

OpenStreetMap contributors. (2024) OpenStreetMap. [Online]. Available: https://www.openstreetmap.org

View on Pith 2024

[21] [21]

P. Alvarez Lopez, A. Banse, M. Barthauer, M. Behrisch, B. Cou ´eraud, J. Erdmann, Y .-P. Fl ¨otter¨od, R. Hilbrich, R. Nippold, and P. Wagner, “Simulation of urban mobility (sumo),” Oct. 2024. [Online]. Available: https://doi.org/10.5281/zenodo.13907886

View on Pith doi:10.5281/zenodo.13907886 2024

[22] [22]

M. Boban. GEMV 2 – geometry-based efficient propagation model for V2V communication. [Online]. Available: http://vehicle2x.net

View on Pith

[23] [23]

Mate Boban, “Geometry-based Efficient propagation Model for V2V communication,” ”https://artery.v2x-research.eu/features/gemv2/”, 2020

View on Pith 2020

[24] [24]

K. Ghosh, C. Bellinger, R. Corizzo, P. Branco, B. Krawczyk, and N. Japkowicz, “The class imbalance problem in deep learning,”Machine Learning, vol. 113, no. 7, pp. 4845–4901, 2024

View on Pith 2024